Battery energy management method, system, medium and product based on intelligent collaboration

Abstract

A method, system, medium, and product for intelligent collaborative battery energy management, relating to the field of energy storage systems, is disclosed. The method includes: collecting real-time current data of the vehicle battery when the driving mode is cruise mode; calculating the dispersion of the real-time current data to obtain a current stability index; collecting terminal voltage, branch current, and temperature data of the vehicle battery when the current stability index is within a preset range to obtain a calibration dataset; inputting the calibration dataset into a battery equivalent circuit model to obtain health characteristic parameters; generating a battery health assessment result based on historical characteristic data and health characteristic parameters in a battery management database; and adjusting the control parameters of the battery charging and discharging strategy and updating the battery health prediction model for predicting the remaining battery life based on the battery health assessment result. Implementing this application enables accurate collection of battery health parameters during daily driving, improving the accuracy of battery energy management.

Description

Technical Field

[0001] This application relates to the field of energy storage systems, and more particularly to a battery energy management method, system, medium, and product based on intelligent collaboration. Background Technology

[0002] With the rapid development of new energy vehicles, the health management of power batteries plays a crucial role in the safety and lifespan of the entire vehicle. The battery management system (BMS) needs to accurately monitor the battery's state of charge (SoC) and state of health (SoH) in real time to optimize charging and discharging strategies, predict remaining lifespan, and promptly identify potential safety hazards.

[0003] In related technologies, BMS mainly uses a combination of ampere-hour integration and open-circuit voltage methods to estimate SoC parameters. For the evaluation of SoH parameters, it typically relies on offline full charge-discharge tests performed at a repair shop to calibrate capacity and internal resistance, and then updates these parameters online during daily use using algorithms such as Kalman filtering.

[0004] In daily driving, complex and varied operating conditions cause large fluctuations in battery internal resistance and capacity measurements, making it difficult to establish a reliable state assessment benchmark. As usage time increases, the accuracy of battery energy management will decrease. Summary of the Invention

[0005] This application provides a battery energy management method, system, medium, and product based on intelligent collaboration, which is used to accurately collect battery health parameters during daily driving and improve the accuracy of battery energy management.

[0006] Firstly, this application provides a battery energy management method based on intelligent collaboration, applied to a battery energy management system. The method includes: collecting real-time current data of the vehicle battery when the vehicle control terminal is in cruise mode; calculating the dispersion of the real-time current data within a statistical period to obtain a current stability index; when the current stability index is within a preset value range, collecting terminal voltage, branch current, and temperature data of the vehicle battery within a preset calibration window time to obtain a calibration dataset; inputting the calibration dataset into a battery equivalent circuit model to obtain health characteristic parameters characterizing the current battery health status; generating a battery health assessment result based on historical characteristic data and health characteristic parameters in a battery management database; and adjusting the control parameters of the battery charging and discharging strategy according to the battery health assessment result, and updating the battery health prediction model that predicts the remaining battery life.

[0007] In the above embodiments, the battery energy management system collects battery data in cruise mode. Combined with current stability assessment and calibration window settings, the accuracy of data collection is ensured. Through equivalent circuit model analysis and comparison with historical data, the battery health status is accurately assessed. At the same time, the charging and discharging strategy is dynamically adjusted and the prediction model is updated based on the assessment results, which improves the adaptability and accuracy of battery management and realizes real-time monitoring and optimized management of battery health status.

[0008] In conjunction with some embodiments of the first aspect, in some embodiments, the step of collecting real-time current data of the vehicle battery when the driving mode of the vehicle control terminal is cruise mode specifically includes: receiving cruise mode parameters sent by the vehicle control terminal; the cruise mode parameters include vehicle speed stability parameters and accelerator pedal position change rate; when the vehicle speed stability parameters are higher than a preset stability threshold and the accelerator pedal position change rate is lower than a preset position change threshold, determining the driving mode as a cruise mode that meets the calibration conditions, and collecting real-time current data of the vehicle battery.

[0009] In the above embodiments, the battery energy management system sets up a dual judgment mechanism of vehicle speed stability and accelerator pedal change rate to ensure the reliability of cruise mode determination. By performing calculations at the battery management system end, the computational load of the vehicle control terminal is reduced, the system resources are rationally allocated, and the accuracy and timeliness of data collection are ensured.

[0010] In conjunction with some embodiments of the first aspect, in some embodiments, the step of generating a battery health assessment result based on historical feature data and health feature parameters in the battery management database specifically includes: comparing the health feature parameters with the historical feature data in the battery management database over time to determine the parameter change rate of the health feature parameters; and generating a battery health assessment result based on the historical feature data and health feature parameters when the parameter change rate is not higher than a preset mutation threshold.

[0011] In the above embodiments, the battery energy management system introduces a parameter change rate threshold judgment mechanism to avoid data anomalies caused by sudden factors, ensure the reliability and continuity of health assessment results, and improve the stability of system operation and the accuracy of data analysis.

[0012] In conjunction with some embodiments of the first aspect, in some embodiments, after the step of inputting the calibration dataset into the battery equivalent circuit model to obtain health characteristic parameters characterizing the current battery health state, the method further includes: when the instantaneous rate of change of the battery output power is detected to be greater than or equal to a preset emergency threshold, temporarily storing the health characteristic parameters and marking the current calibration process as an abnormal interruption state; after the instantaneous rate of change recovers to below the preset emergency threshold, determining the abnormal duration of the abnormal interruption state; and when the abnormal duration is greater than or equal to a preset time threshold, re-collecting the real-time current data of the vehicle battery.

[0013] In the above embodiments, the battery energy management system introduces a battery output power instantaneous change rate monitoring mechanism. Through abnormal interruption status marking and data temporary storage, it realizes rapid response to sudden operating conditions. The judgment mechanism based on the abnormal duration ensures the continuity and reliability of the data acquisition process.

[0014] In conjunction with some embodiments of the first aspect, in some embodiments, after determining the abnormal duration of the abnormal interruption state, the method further includes: when the abnormal duration is less than a preset time threshold, reading temporarily stored health feature parameters; comparing the health feature parameters with historical feature data in the battery management database in a time series, and generating a battery health assessment result based on the historical feature data and the health feature parameters.

[0015] In the above embodiments, the battery energy management system ensures the system's continuous operation under micro-interference conditions through a special handling mechanism for short-term abnormal situations, thereby improving the system's fault tolerance and working efficiency.

[0016] In conjunction with some embodiments of the first aspect, in some embodiments, after adjusting the control parameters of the battery charging and discharging strategy and updating the battery health prediction model for predicting the remaining battery life based on the battery health assessment results, the method further includes: calculating the predicted battery performance value for a future preset time period based on the adjusted control parameters and the updated battery health prediction model; collecting measured battery performance values ​​during actual operation and calculating the prediction deviation between the predicted battery performance value and the measured battery performance value; and correcting the model parameters of the battery health prediction model based on the prediction deviation value when the prediction deviation value exceeds a preset deviation threshold.

[0017] In the above embodiments, the battery energy management system achieves adaptive adjustment of model parameters by introducing a comparison mechanism between predicted and measured values, thereby improving the accuracy and reliability of the prediction model.

[0018] In conjunction with some embodiments of the first aspect, in some embodiments, before the step of correcting the model parameters of the battery health prediction model based on the prediction deviation value, the method further includes: collecting temperature sampling data of the environment in which the battery is located; classifying the prediction deviation value according to the interval distribution of the temperature sampling data to obtain temperature interval deviation data; updating the temperature correction parameters of the battery health prediction model according to the temperature interval deviation data, and correcting the prediction deviation value.

[0019] In the above embodiments, the battery energy management system improves the model's adaptability to different temperature environments by introducing a temperature range classification and correction mechanism, thereby achieving more accurate battery performance prediction.

[0020] In a second aspect, embodiments of this application provide a battery energy management system, which includes: one or more processors and a memory; the memory is coupled to the one or more processors, and the memory is used to store computer program code, the computer program code including computer instructions, and the one or more processors call the computer instructions to cause the battery energy management system to perform the method described in the first aspect and any possible implementation thereof.

[0021] Thirdly, embodiments of this application provide a computer program product containing instructions that, when the computer program product is run on a battery energy management system, cause the battery energy management system to perform the method described in the first aspect and any possible implementation thereof.

[0022] Fourthly, embodiments of this application provide a computer-readable storage medium including instructions that, when executed on a battery energy management system, cause the battery energy management system to perform the method described in the first aspect and any possible implementation thereof.

[0023] Understandably, the battery energy management system provided in the second aspect, the computer program product provided in the third aspect, and the computer storage medium provided in the fourth aspect are all used to execute the methods provided in the embodiments of this application. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects in the corresponding methods, and will not be repeated here.

[0024] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages: 1. By adopting the above technical solution, and utilizing the current stability assessment and calibration window acquisition mechanism in cruise mode, high-quality battery parameter data can be obtained under stable operating conditions. This effectively solves the data fluctuation problem caused by complex and variable operating conditions in existing technologies, thereby achieving accurate assessment of battery health status. Cruise mode ensures stable operating conditions, and the current stability index further filters for appropriate data acquisition opportunities. The collected calibration dataset is then analyzed in conjunction with the equivalent circuit model, enabling accurate assessment of battery health status. Based on this, charging and discharging strategies can be optimized, achieving closed-loop optimization of battery management.

[0025] 2. By adopting the above technical solution, and employing a dual judgment mechanism based on vehicle speed stability parameters and accelerator pedal position change rate, the system can accurately identify cruise conditions that meet calibration requirements. This effectively solves the problem of insufficient accuracy and simplistic cruise state judgment in existing technologies, thereby achieving precise control over data acquisition timing. By monitoring vehicle speed stability and driver operating characteristics, data acquisition is ensured to occur under the most suitable conditions. The computational tasks are then transferred to the battery management system, avoiding excessive computational load on the vehicle control terminal and improving the overall system efficiency.

[0026] 3. By adopting the above technical solution, and employing an anomaly detection mechanism based on the instantaneous change rate of battery output power and a data temporary storage strategy, it can respond promptly to sudden operating conditions and protect acquired data. This effectively solves the problem of data loss or distortion caused by sudden operating conditions in existing technologies, thereby ensuring the reliability of the data acquisition process. By monitoring changes in battery output power in real time, data is immediately temporarily stored and its status marked when an anomaly is detected. After the anomaly ends, the duration determines whether re-acquisition is necessary, ensuring data integrity and availability. Attached Figure Description

[0027] Figure 1 This is a flowchart illustrating a battery energy management method based on intelligent collaboration in an embodiment of this application. Figure 2 This is another flowchart illustrating the battery energy management method based on intelligent collaboration in this application embodiment; Figure 3 This is a schematic diagram of the physical device structure of a battery energy management system in the embodiments of this application. Detailed Implementation

[0028] The terminology used in the following embodiments of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of this application. As used in the specification of this application, the singular expressions “a,” “an,” “the,” “the,” and “this” are intended to include the plural expressions as well, unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used in this application refers to any or all possible combinations including one or more of the listed items.

[0029] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature, and in the description of the embodiments of this application, unless otherwise stated, "multiple" means two or more.

[0030] To facilitate understanding, the application scenarios of the embodiments of this application are described below.

[0031] With the increasing popularity of new energy vehicles, the health management of power batteries is becoming increasingly important. In actual driving, the battery management system (BMS) needs to monitor the battery's state of charge (SoC) and state of health (SoH) in real time to optimize charging and discharging strategies and predict remaining lifespan. However, due to the complex and varied driving conditions, battery parameters fluctuate significantly, making it difficult to establish reliable evaluation benchmarks. Especially during daily driving, accurately measuring health parameters such as battery capacity and internal resistance becomes a major challenge. Failure to obtain accurate battery health data in a timely manner may lead to decreased battery management accuracy, affecting battery lifespan and overall vehicle safety.

[0032] In related technologies, battery health status can be assessed and managed through regular maintenance and online parameter estimation. The following describes a scenario using a smart collaborative battery energy management method from this technology.

[0033] Traditional battery management solutions primarily rely on offline full charge-discharge cycles performed at repair shops to calibrate capacity and internal resistance parameters. In daily use, the BMS estimates the System-on-Chips (SoC) using a combination of ampere-hour integration and open-circuit voltage methods, and updates the parameters online using algorithms such as Kalman filtering. However, this method has significant drawbacks: first, offline calibration requires the vehicle to be parked for extended periods, impacting user experience; second, parameter fluctuations under complex operating conditions affect the accuracy of online estimation; and finally, as usage time increases, parameter drift leads to a continuous decline in management accuracy.

[0034] The intelligent collaborative battery energy management method described in this application achieves accurate parameter calibration during daily driving through steady-state data acquisition and real-time health assessment in cruise mode. This not only avoids additional offline detection time but also improves the accuracy of the assessment results. The following describes scenarios where the intelligent collaborative battery energy management method of this application is used.

[0035] Using the intelligent collaborative management method of this application, the system automatically detects current stability during vehicle cruise mode. When the current stability index meets the requirements, the system collects battery parameter data within the calibration window and obtains health characteristic parameters through equivalent circuit model analysis. These parameters are compared and analyzed with historical data to generate real-time health assessment results, and the charging and discharging strategy is dynamically adjusted accordingly. This solution can automatically complete parameter calibration during daily driving without additional stopping for testing, ensuring the accuracy and reliability of the data.

[0036] As can be seen, the intelligent collaborative battery energy management method in this application embodiment can not only achieve real-time assessment of battery health status, but also effectively solve the problems of parameter drift and accuracy degradation in traditional methods, thereby realizing continuous optimization of the battery management system.

[0037] To facilitate understanding, the method provided in this implementation will be described in detail below, using the above scenario as an example. Please refer to [link / reference]. Figure 1 This is a flowchart illustrating a battery energy management method based on intelligent collaboration in an embodiment of this application.

[0038] S101. When the driving mode of the vehicle control terminal is cruise mode, collect the real-time current data of the vehicle battery.

[0039] Among them, the vehicle control terminal refers to the core control device installed on the vehicle for controlling and monitoring the vehicle's operating status; cruise mode indicates the state of the vehicle continuously driving at a relatively stable speed; real-time current data refers to the real-time measurement value of the battery charging and discharging current collected by the current sensor, and the unit is ampere (A).

[0040] Specifically, the battery energy management system triggers this step when it detects that the vehicle has entered cruise control mode. The battery energy management system first confirms that the driving mode signal sent by the vehicle control terminal indicates that cruise control is currently in effect. Then, it activates the current data acquisition module to continuously acquire the battery's charging and discharging current values ​​at a preset sampling frequency (e.g., 100Hz). The acquired data includes the current amplitude, direction (positive for charging, negative for discharging), and corresponding timestamp information. The battery energy management system temporarily stores the acquired data in a system cache to prepare for subsequent current stability analysis.

[0041] In practical applications, current data acquisition may be affected by factors such as electromagnetic interference and sensor accuracy drift. To address this issue, the battery energy management system employs an adaptive filtering algorithm and a sensor self-calibration mechanism. Specifically, the system periodically performs sensor zero-point calibration when the current is zero; during data processing, it dynamically adjusts filtering parameters based on historical data characteristics; and it sets reasonable data validity judgment criteria to ensure the reliability of the acquired data. When a sensor anomaly is detected, the system automatically switches to a backup sensor channel and reports the abnormal status to the upper-level control system.

[0042] S102. Calculate the dispersion of real-time current data within a statistical period to obtain the current stability index.

[0043] Among them, the statistical period represents the time window for current data analysis, which is usually 10-30 seconds; the dispersion refers to the degree of dispersion of the data distribution, which is used to quantify the current fluctuation; the current stability index is a dimensionless index that characterizes the stability of the battery's operating current, and its value ranges from 0 to 1. The closer the value is to 1, the more stable the current is.

[0044] Specifically, the battery energy management system performs sliding window processing on the collected real-time current data. The system first determines the length of the statistical period, and then calculates the statistical characteristics of the current data within this time window. The calculation process includes obtaining statistical quantities such as the current mean, standard deviation, and peak-to-peak value, and then calculating the dispersion based on these characteristics using a preset algorithm. Finally, the system maps the dispersion to a standardized current stability index range to obtain a quantitative indicator reflecting the current current stability. This indicator will be used to determine whether the conditions for battery parameter calibration are met.

[0045] In some embodiments, current stability analysis can be implemented in the following ways: Optionally, the battery energy management system employs a variance-based method, first calculating the root mean square error of the current data within a statistical period, then calculating the coefficient of variation by combining the current mean, and finally mapping the coefficient of variation to a current stability index using a nonlinear function; the system also considers the rate of change of current and performs weighted processing on rapidly changing intervals. Optionally, the battery energy management system employs a frequency domain-based method, analyzing the spectral characteristics of the current signal through fast Fourier transform; calculating the energy proportion of the dominant frequency component; and comprehensively evaluating the stability of the current by combining time-domain and frequency-domain characteristics.

[0046] S103. When the current stability index is within the preset value range, collect the terminal voltage, branch current and temperature data of the vehicle battery within the preset calibration window time to obtain the calibration dataset.

[0047] Among them, the preset value range represents the current stability requirement required for battery parameter calibration, which is usually 0.85-0.95; the calibration window time refers to the sampling period required to perform a complete calibration, which is usually 1-5 minutes; the terminal voltage refers to the potential difference between the positive and negative terminals of the battery; the branch current refers to the shunt current of each parallel branch of the battery; and the calibration dataset refers to the collection of multi-dimensional sampling data used for battery parameter identification.

[0048] Specifically, after confirming that the current stability index meets the requirements, the battery energy management system initiates a multi-parameter parallel acquisition process. The system first checks the operating status of all sensors to ensure the data acquisition channels are functioning correctly. Then, the system synchronously acquires battery terminal voltage, current in each branch, and temperature data of the battery surface, internal structure, and environment according to a preset sampling frequency. During the acquisition process, the system monitors the validity and completeness of the data in real time to ensure sampling quality. Finally, the system organizes the acquired multidimensional data according to time series to form a structured calibration dataset and performs data preprocessing, including outlier detection and data standardization.

[0049] In some embodiments, multi-parameter data acquisition can be achieved in the following ways: Optionally, the battery energy management system adopts a distributed data acquisition architecture, configuring an independent sampling unit in each battery module, and realizing synchronous data acquisition and transmission via a CAN bus; the system uses a high-precision voltage sampling chip and temperature sensor array to achieve a voltage measurement accuracy of ±0.1% and a temperature measurement accuracy of ±0.5℃; real-time quality assessment is performed on the acquired data, including data continuity checks and range validity verification. Optionally, the battery energy management system implements an adaptive sampling strategy, dynamically adjusting the sampling frequency according to the data change rate; establishes a data redundancy storage mechanism to ensure the reliability of critical data; and uses data compression algorithms to reduce storage and transmission load.

[0050] S104. Input the calibration dataset into the battery equivalent circuit model to obtain health characteristic parameters that characterize the current battery health status.

[0051] Among them, the battery equivalent circuit model refers to a mathematical model that uses circuit elements to simulate the electrochemical characteristics of the battery, and usually includes basic components such as resistors and capacitors; health characteristic parameters include key indicators that reflect the degree of battery performance degradation, such as ohmic internal resistance, polarization internal resistance, and double-layer capacitance.

[0052] Specifically, the battery energy management system first selects a suitable equivalent circuit model structure based on the battery type and operating characteristics. The system then converts and normalizes the preprocessed calibration dataset according to the model requirements before inputting it into the parameter identification algorithm. Through iterative calculations using the optimization algorithm, the system finds the parameter combination that best matches the model output with the measured data. During parameter identification, the system considers the influence of factors such as temperature and state of charge, and corrects the parameters accordingly. The final set of health characteristic parameters reflects the current performance state of the battery, and these parameters will be used for subsequent health assessments.

[0053] It should be noted that the battery equivalent circuit model simulates the electrochemical characteristics of the battery through an RC network structure, mainly including an open-circuit voltage source, series internal resistance, and multiple parallel RC branches. The model's input data includes sampled battery terminal voltage, branch current, and temperature data. This data is first high-pass filtered to remove DC bias, and then fitted using the least squares method to obtain the time constant and impedance parameters of each RC branch. The model's state equations are discretized, and the parameters are identified in real time using a Kalman filter algorithm. During the identification process, parameters are compensated and corrected based on temperature data to establish parameter mapping relationships for different temperature ranges. The output health characteristic parameters include series internal resistance, polarization internal resistance, and equivalent capacitance, which directly reflect the degree of battery degradation. For example, at 25°C, the typical series internal resistance of a new battery is 0.5 mΩ, and the polarization internal resistance is 1.2 mΩ. As the number of cycles increases, these parameters gradually increase. When the series internal resistance increases to 1.5 times the initial value, it indicates that the battery has entered the degradation phase. In practical applications, the parameter identification process may encounter problems such as model structure mismatch or local optima. To address this issue, the battery energy management system employs an adaptive model selection mechanism. Specifically, the system establishes a multi-level equivalent circuit model library, including first-order RC models, second-order RC models, and extended Thevenin models. By analyzing battery response characteristics, the system automatically selects the model structure most suitable for the current operating conditions. Simultaneously, the system implements a reliability assessment function for parameter identification: by calculating the goodness of fit between the model output and measured data, the accuracy of parameter identification is evaluated; a parameter change rate limit is set to avoid parameter abrupt changes due to data noise; and a historical parameter database is established to verify the rationality of the current results using historical identification results. When abnormal parameter identification results are detected, the system automatically adjusts the parameters of the optimization algorithm or switches to a backup algorithm for re-identification. The system also considers the impact of temperature on parameters, establishing a parameter-temperature relationship model to achieve temperature compensation for parameters.

[0054] S105. Based on historical feature data and health feature parameters in the battery management database, generate battery health assessment results.

[0055] Among them, the battery management database is a structured information system that stores historical data of battery operation, including historical records such as battery parameters, operating conditions, and performance degradation; historical characteristic data refers to the set of health characteristic parameters acquired by the battery at different times; battery health assessment results include quantitative indicators such as capacity decay rate, internal resistance growth rate, and remaining capacity, as well as the corresponding health level determination.

[0056] Specifically, the battery energy management system first extracts historical characteristic data of the battery from the database and establishes a trend chart of parameter changes over time. The system compares and analyzes the currently acquired health characteristic parameters with historical data, calculating the rate of change and cumulative change of each parameter. Through a preset health assessment model, the system comprehensively considers the changes of multiple characteristic parameters to calculate the battery's overall health index. During the assessment process, factors such as the battery's usage environment and charge / discharge history are considered, and the assessment results are corrected accordingly. Finally, a health assessment report containing quantitative indicators and qualitative ratings is generated.

[0057] S106. Based on the battery health assessment results, adjust the control parameters of the battery charging and discharging strategy, and update the battery health prediction model that predicts the remaining battery life.

[0058] Among them, the control parameters of the charge and discharge strategy include key operating parameters such as charging cut-off voltage, maximum charge and discharge current, and equalization control threshold; the battery health prediction model is a mathematical model used to estimate the remaining battery life, including a degradation mechanism model and a data-driven model; the remaining life prediction covers the prediction results of multiple performance indicators such as capacity decay and internal resistance growth.

[0059] Specifically, the battery energy management system first determines the battery's current performance level based on the health assessment results. The system then queries a pre-set parameter adjustment strategy table based on the performance level to generate a new set of charge and discharge control parameters. These parameter adjustments follow a balance between performance and lifespan, maximizing battery lifespan while meeting user needs. Simultaneously, the system inputs the latest health assessment results into the health prediction model, updates the model parameters, and recalculates the battery's remaining lifespan prediction. The prediction process considers the impact of historical usage patterns and environmental factors, providing lifespan prediction results under various usage scenarios.

[0060] It should be noted that the battery health prediction model employs a deep learning-based bidirectional long short-term memory (Bi-LSTM) network structure. Input features include historical sequences of health characteristic parameters, cumulative charge / discharge cycles, temperature distribution statistics, and load characteristics, among other multi-dimensional data. The model first normalizes the input data, then extracts temporal features through multiple layers of Bi-LSTM units. Each LSTM unit has a hidden layer dimension of 128, and a dropout mechanism (probability 0.3) is used to prevent overfitting. Model training utilizes the Adam optimizer with an initial learning rate of 0.001, dynamically adjusted using a cosine annealing strategy. The loss function combines mean squared error and a custom capacity decay penalty term to balance short-term prediction accuracy with long-term trend fitting. The model output includes predicted values ​​for health indicators such as capacity decay rate and internal resistance growth rate over a preset future time period, along with upper and lower limits for the 95% confidence interval. The root mean square error (RMSE) between the prediction results and measured data is controlled within 3%, and reliable predictions can be made over a period of up to 3 months. The model is periodically fine-tuned online using newly collected data for continuous optimization. For example, for a typical lithium iron phosphate battery, the model can accurately predict the capacity degradation trend over the next month under normal operating conditions. The prediction results show that the natural monthly capacity degradation rate is approximately 0.2%-0.3%.

[0061] In some embodiments, strategy adjustment and lifetime prediction can be achieved through the following methods: Optionally, the battery energy management system adopts a rule-based adaptive control strategy to establish a mapping relationship between health status and control parameters; designs a hierarchical control structure to achieve coordinated control for rapid response and long-term optimization; and introduces an operating condition prediction mechanism to adjust the control strategy in advance. Optionally, the battery energy management system adopts a deep learning-based lifetime prediction method to construct a prediction model of multi-factor coupling effects; utilizes transfer learning technology to improve the generalization ability of the model; and combines uncertainty quantification methods to provide confidence intervals for the prediction results.

[0062] In the above embodiment, the reliability of the collected data is ensured by setting the current stability index and calibration window. In practical applications, the system can also flexibly adjust the calibration strategy based on multi-dimensional parameters such as vehicle speed stability and accelerator pedal changes. The following section supplements the scenario described in this embodiment.

[0063] In practical applications, the system also comprehensively considers factors such as vehicle speed stability and accelerator pedal changes to ensure the reliability of calibration conditions. In emergency situations, the system temporarily stores data and handles anomalies. Furthermore, by establishing a temperature range deviation model, the system can correct predictions under different ambient temperatures, further improving evaluation accuracy. This multi-dimensional optimization ensures the stability and reliability of battery management under various complex operating conditions.

[0064] In light of the above scenarios, the method provided in this implementation will now be described in more detail. Please refer to [link / reference]. Figure 2 This is another flowchart illustrating the battery energy management method based on intelligent collaboration in this application embodiment.

[0065] S201, Receive cruise mode parameters sent by the vehicle control terminal.

[0066] Among them, the vehicle control terminal refers to the central processing unit used to control the vehicle's driving status, including hardware devices such as the vehicle controller and cruise controller; cruise mode parameters refer to various data indicators that describe the vehicle's cruise status, including target cruise speed, actual driving speed, speed deviation, accelerator pedal position, cruise control status indicators, etc.

[0067] Specifically, after the vehicle enters cruise mode, the battery energy management system receives cruise-related parameters from the vehicle control terminal in real time via the CAN bus. First, the battery energy management system confirms the communication link is functioning correctly, and then initializes the parameter receiving buffer. The system parses the received data frames according to a preset communication protocol, extracts the cruise mode parameters, and verifies their validity. After successful verification, the system stores the parameters in a designated data area, preparing for subsequent calibration condition checks. During parameter reception, the system records the data timestamps to ensure data sequence.

[0068] In practical applications, cruise parameter reception may encounter communication interruptions or data loss. To address this issue, the battery energy management system employs multiple data reliability assurance mechanisms. Specifically, the system implements a communication quality monitoring function, detecting the CAN bus communication status and bit error rate in real time. When a decline in communication quality is detected, the system initiates a data compensation algorithm to fill in lost data through historical data interpolation or calculation based on adjacent parameters. Simultaneously, the system establishes a parameter validity evaluation mechanism, filtering abnormal data by setting a reasonable range for parameter changes. The system also implements a data retransmission request function, sending a retransmission request to the vehicle control terminal when critical parameters are detected as lost. To cope with prolonged communication interruptions, the system is designed with a degraded operation mode, which can maintain basic functions based on the most recently valid parameters.

[0069] S202. When the vehicle speed stability parameter is higher than the preset stability threshold and the accelerator pedal position change rate is lower than the preset position change threshold, the driving mode is determined to be the cruise mode that meets the calibration conditions, and the real-time current data of the vehicle battery is collected.

[0070] Among them, the vehicle speed stability parameter is a quantitative indicator of the degree of fluctuation in vehicle speed, usually expressed by the speed standard deviation or coefficient of variation; the preset stability threshold is the critical value for judging vehicle speed stability, usually set to a standard deviation of no more than 2 km / h; the accelerator pedal position change rate is the amount of change in the accelerator pedal opening per unit time, used to characterize the frequency of the driver's acceleration operation; the preset position change threshold is usually set to 5% / s; cruise mode refers to the state in which the vehicle automatically controls its driving at a stable speed; real-time current data refers to the instantaneous current sampling value during the battery charging and discharging process.

[0071] Specifically, the battery energy management system first processes the received vehicle speed data using a sliding window method to calculate the vehicle speed stability parameter within a specified time window. The system uses the least squares method to calculate the dispersion of the speed data and compares it with a preset stability threshold. Simultaneously, the system calculates the first derivative of the accelerator pedal position signal to obtain the rate of change of position. When both the vehicle speed stability parameter and the accelerator pedal position change rate meet the threshold conditions, the system confirms that the current driving state meets the calibration requirements for cruise mode. After confirmation, the system immediately initiates the battery current acquisition program, acquiring real-time current data from each branch of the battery through a high-precision sampling circuit. During the acquisition process, the system continuously monitors the stability of vehicle speed and pedal status to ensure that the calibration conditions are continuously met.

[0072] In practical applications, cruise control status judgment may encounter the problem of frequent switching of judgment results due to short-term fluctuations in vehicle speed. To solve this problem, the battery energy management system adopts a state hysteresis control mechanism. Specifically, the system designs a dual-threshold judgment structure, using different threshold standards for entering and exiting cruise mode, forming a hysteresis interval between the two thresholds. The system also implements a state maintenance time requirement, requiring a stable state to last for a certain period of time before triggering a mode switch. Simultaneously, the system establishes a predictive judgment mechanism, analyzing the trend characteristics of vehicle speed and pedal operation to predict state change trends in advance. For instantaneous fluctuations, the system uses a low-pass filtering algorithm for smoothing, reducing false judgments. The system also records judgment results under historical operating conditions to optimize judgment parameters and improve the algorithm's adaptability.

[0073] S203. Calculate the dispersion of real-time current data within a statistical period to obtain the current stability index.

[0074] Referring to step S102, the battery energy management system will calculate the fluctuation of current data over a period of time to evaluate the battery's operational stability.

[0075] S204. When the current stability index is within the preset value range, collect the terminal voltage, branch current and temperature data of the vehicle battery within the preset calibration window time to obtain the calibration dataset.

[0076] Referring to step S103, the battery energy management system will collect key battery operating parameter data when stable conditions are met.

[0077] S205. Input the calibration dataset into the battery equivalent circuit model to obtain health characteristic parameters that characterize the current battery health status.

[0078] Referring to step S104, the battery energy management system will analyze and process the calibration data through an equivalent circuit model to assess the battery's health status.

[0079] S206. When the instantaneous rate of change of the battery output power is detected to be greater than or equal to the preset emergency threshold, the health characteristic parameters are temporarily stored and the current calibration process is marked as an abnormal interruption state.

[0080] Among them, battery output power represents the instantaneous power value actually output by the battery, which is calculated by multiplying the battery voltage and current; instantaneous change rate refers to the amount of power change per unit time, used to characterize the severity of power fluctuation; preset emergency threshold is usually set to 30% / s of rated power; health characteristic parameters refer to key indicators reflecting the battery performance status, including internal resistance, capacity, etc.; abnormal interruption status indicates the working state in which the calibration process is forced to stop due to fault or abnormality.

[0081] Specifically, the battery energy management system continuously monitors the battery's output power. The system first collects high-frequency sampling data of the battery terminal voltage and output current to calculate the real-time power value. Then, the system uses a differential method to calculate the instantaneous rate of change of power and compares the calculation result with a preset emergency threshold. When the instantaneous rate of change exceeds the threshold, the system immediately initiates an emergency protection process: first, all currently acquired health characteristic parameters are written to a temporary storage area to ensure data is not lost; simultaneously, the calibration status flag is modified to set it to an abnormal interruption state. The system also records the specific time and power data that triggered the anomaly for subsequent analysis. After completing these operations, the system continues to monitor power changes, waiting for the abnormal state to be resolved.

[0082] In practical applications, power surge detection may encounter false triggering issues due to signal noise. To address this problem, the battery energy management system employs an anti-interference detection mechanism. Specifically, the system implements a multi-filtering strategy: first, median filtering is applied to the original power signal to remove sudden noise; then, the power data is smoothed using a Kalman filter algorithm; finally, a bandpass filter is used to extract the effective power change signal. The system also establishes an adaptive window mechanism for calculating the rate of change, dynamically adjusting the calculation window size based on the characteristics of the power signal. Simultaneously, the system implements a tiered triggering strategy: for slight threshold exceedances, the system extends the judgment time to confirm whether it is a persistent anomaly; for severe threshold exceedances, the system immediately triggers a protection mechanism. The system also records the characteristic patterns of historical anomaly triggers to optimize the parameter settings of the detection algorithm.

[0083] S207. After the instantaneous rate of change recovers to below the preset emergency threshold, determine the abnormal duration of the abnormal interruption state.

[0084] Among them, instantaneous change rate recovery indicates the process of the battery output power change rate returning to a safe range; preset emergency threshold refers to the critical value for determining whether the power change is abnormal, usually 30% / s of the rated power; abnormal duration refers to the time interval from the detection of power abnormality to the power returning to normal; abnormal interruption status indicates that the calibration process is in a working state that is suspended due to a fault.

[0085] Specifically, after detecting a drop in the instantaneous rate of power change below a preset emergency threshold, the battery energy management system initiates an abnormal time statistics process. The system first reads the timestamp of the abnormality trigger, then obtains the timestamp of the power recovery, and calculates the abnormal duration by the difference between the two timestamps. During the calculation, the system verifies the stability of the power recovery, requiring the power change rate to remain below the threshold for a sustained period before confirming effective recovery. The system associates and stores the calculated abnormal duration with relevant abnormal information for subsequent processing decisions. Simultaneously, the system continuously monitors the power status to prevent repeated fluctuations.

[0086] S208. When the abnormal duration is greater than or equal to the preset time threshold, the real-time current data of the vehicle battery is collected again.

[0087] Among them, the preset time threshold is the critical time value for determining whether recalibration is needed, which is usually set to 10-30 seconds; real-time current data refers to the instantaneous current sampling value that reflects the battery's working state, including total current and branch current; re-acquisition means abandoning the data of the current calibration process and restarting the data acquisition process; vehicle battery refers to the power battery pack installed on the vehicle, including multiple parallel battery modules.

[0088] Specifically, the battery energy management system first compares the calculated duration of the anomaly with a preset time threshold. When the anomaly duration exceeds the threshold, the system determines that the current calibration data is no longer usable and data acquisition needs to be performed again. The system then executes a calibration reset process: first, it clears all temporary data acquired during the current calibration process; then, it reinitializes the configuration parameters of the data acquisition module; next, it checks the working status of the acquisition channels to ensure that all sensors are working properly; finally, it starts a new data acquisition program to reacquire the battery's real-time current data according to the preset sampling strategy. Throughout the entire reacquisition process, the system continuously monitors the battery status to ensure that the calibration conditions are met.

[0089] In practical applications, the re-acquisition process may encounter problems such as unstable battery status leading to unsatisfactory acquisition results. To address this issue, the battery energy management system employs an intelligent acquisition control mechanism. Specifically, the system implements a status pre-check function: before initiating a new acquisition process, it first conducts a comprehensive assessment of the battery's operating status, including key parameters such as voltage stability, temperature distribution, and state of charge; only when all status parameters meet the requirements does formal acquisition begin. Simultaneously, the system establishes a dynamic optimization mechanism for acquisition parameters: it automatically adjusts acquisition configurations such as sampling frequency and filtering parameters based on the current battery status; for different types of abnormal situations, the system selects appropriate acquisition strategies. The system also implements a segmented acquisition function: when battery status fluctuates significantly, the acquisition process can be divided into multiple time periods, with each time period undergoing independent data quality assessment, retaining only data segments that meet the requirements. For abnormal situations occurring during the acquisition process, the system will promptly adjust acquisition parameters or temporarily pause acquisition, waiting for conditions to improve before resuming. Furthermore, the system records the process data from each re-acquisition for optimizing acquisition strategies and preventing anomalies.

[0090] In some embodiments, the battery energy management system will continue the subsequent health assessment when the interruption time is short. That is, when the duration of the abnormality is less than a preset time threshold, the battery energy management system will read the temporarily stored health feature parameters; compare the health feature parameters with the historical feature data in the battery management database in a time series; and generate the battery health assessment result based on the historical feature data and the health feature parameters.

[0091] Among them, the abnormal duration refers to the duration for which the battery power fluctuation exceeds the normal range; the preset time threshold refers to the critical time value for judging whether the abnormality affects the calibration validity, which is usually 10-30 seconds; the temporarily stored health characteristic parameters refer to the battery performance index data temporarily saved when the abnormality occurs; the historical characteristic data refers to the parameter records obtained from each calibration stored in the database; the time series comparison refers to the parameter change analysis process based on the time sequence; and the health assessment results are used to characterize the current performance and life status of the battery.

[0092] Specifically, the battery energy management system first determines whether the duration of the abnormal state exceeds a preset threshold. If the duration is short, the system considers the impact of the abnormality on the calibration process to be limited, and the acquired data can continue to be used. The system reads the health characteristic parameters saved at the time of the abnormality from the temporary storage area and verifies the data integrity. Then, it accesses the database to obtain the battery's historical characteristic data and compares the current parameters with the historical data. By analyzing the changing trends and distribution characteristics of the parameters, and combining this with a preset evaluation model, the system generates a health assessment result reflecting the battery's current state. Throughout the process, the system records the specific circumstances of the abnormality for subsequent strategy optimization.

[0093] S209. Generate battery health assessment results based on historical feature data and health feature parameters in the battery management database.

[0094] Referring to step S105, the battery energy management system will compare and analyze the current health status with historical data.

[0095] In some embodiments, the battery energy management system performs a parameter change rate check. That is, the battery energy management system compares the health characteristic parameters with historical characteristic data in the battery management database over time to determine the parameter change rate of the health characteristic parameters. When the parameter change rate is not higher than a preset mutation threshold, a battery health assessment result is generated based on the historical characteristic data and the health characteristic parameters.

[0096] Among them, health characteristic parameters represent the set of key indicators reflecting the battery performance status obtained during the current calibration process, including ohmic internal resistance, polarization internal resistance, double-layer capacitance, etc.; the battery management database refers to a structured information system that stores the battery's operational data throughout its entire life cycle; historical characteristic data represents the records of health characteristic parameters obtained during previous calibration processes; time-series comparison refers to the analysis process of comparing the trend of parameter changes in chronological order; parameter change rate is used to represent the speed at which health characteristic parameters change over time; preset mutation threshold is the critical value for judging whether parameter changes are abnormal, usually set to 5%-10% of the nominal value; and health assessment results represent a comprehensive evaluation of the battery's current performance and lifespan status.

[0097] Specifically, after acquiring new health characteristic parameters, the battery energy management system first extracts historical characteristic data records of the battery from the database. The system then arranges the newly acquired parameters and historical data in chronological order to create a parameter change trend chart. By calculating the parameter differences between adjacent time points and performing time normalization, the system obtains the change rate of each characteristic parameter. For each parameter, the system compares its change rate with a corresponding preset mutation threshold. When the change rate of all parameters does not exceed the threshold, the system considers the current data reliable. Subsequently, based on complete parameter time-series data, it uses a preset evaluation algorithm to generate an evaluation result reflecting the battery's current health status.

[0098] In practical applications, time-series parameter analysis may encounter problems such as inaccurate rate of change calculations due to discontinuous historical data. To address this issue, the battery energy management system employs a data compensation mechanism. Specifically, the system implements a data integrity assessment function: first, it examines the time distribution of historical data to identify missing data intervals; then, it selects an appropriate compensation strategy based on the type of missing data—interpolation for short-term missing data and estimation based on a degradation model for long-term missing data; simultaneously, it establishes a data reliability scoring mechanism to assess the quality of the compensated data. The system also implements multi-timescale rate of change analysis, improving the reliability of calculation results by comparing the change characteristics across different time spans. For detected abnormal changes, the system initiates a cross-validation process, combining other relevant parameters for comprehensive judgment to avoid misjudgments caused by a single parameter.

[0099] S210. Based on the battery health assessment results, adjust the control parameters of the battery charging and discharging strategy, and update the battery health prediction model that predicts the remaining battery life.

[0100] Referring to step S106, the battery energy management system will optimize the charging and discharging strategy and update the life prediction model based on the evaluation results.

[0101] In some embodiments, the battery energy management system performs prediction correction, that is, the battery energy management system calculates the predicted battery performance value for a future preset time period based on the adjusted control parameters and the updated battery health prediction model; collects the measured battery performance value during actual operation, calculates the prediction deviation value between the predicted battery performance value and the measured battery performance value; and when the prediction deviation value exceeds a preset deviation threshold, corrects the model parameters of the battery health prediction model based on the prediction deviation value.

[0102] Among them, control parameters refer to key control variables used to manage the battery charging and discharging process, including charging cut-off voltage, maximum charging and discharging current, etc.; battery health prediction model refers to the mathematical model used to predict future performance changes of the battery; preset time period is usually a prediction cycle of 1-6 months; battery performance prediction value refers to the performance index at a certain future moment calculated by the model; battery performance measured value refers to the performance data measured in actual operation; prediction deviation value is used to represent the degree of difference between the predicted value and the measured value; preset deviation threshold refers to the deviation critical value that triggers model correction, usually 5%-10% of the predicted value; model parameters refer to the adjustable variables in the prediction model.

[0103] Specifically, the battery energy management system first loads the latest adjusted control parameters and updated prediction model into the computing environment. Based on the current battery state and a preset time step, the system iteratively calculates and generates a performance prediction sequence for a future period. During actual operation, the system continuously collects various battery performance indicators and compares these measured data with previous predictions. The system calculates the prediction deviation at each time point and performs statistical analysis. When the prediction deviation exceeds a preset threshold, the system initiates a model correction process, optimizing and adjusting the model parameters based on the deviation characteristics to improve prediction accuracy.

[0104] In practical applications, performance prediction may encounter the problem of prediction model failure due to changes in operating conditions. To address this issue, the battery energy management system employs an adaptive prediction mechanism based on operating conditions. Specifically, the system implements operating condition feature identification: by analyzing battery usage patterns and environmental conditions, it identifies typical operating condition types; establishes an operating condition-performance mapping relationship to assess the impact of operating condition changes on performance prediction; and dynamically adjusts the parameters and structure of the prediction model based on operating condition characteristics. The system also establishes a hierarchical prediction framework: for short-term predictions, it prioritizes current operating condition characteristics, while for long-term predictions, it relies more on statistical regularities. When a significant change in operating conditions is detected, the system activates a rapid response mechanism: temporarily reducing the prediction time domain and increasing the prediction frequency; simultaneously, it collects operational data under the new operating conditions for online model learning and updates. By establishing an operating condition library and a corresponding prediction model library, the system achieves rapid adaptation to different operating conditions.

[0105] In some embodiments, the battery energy management system performs temperature correction on the prediction deviation values. Specifically, the battery energy management system collects temperature sampling data of the environment in which the battery is located; classifies the prediction deviation values ​​according to the interval distribution of the temperature sampling data to obtain temperature interval deviation data; updates the temperature correction parameters of the battery health prediction model based on the temperature interval deviation data, and corrects the prediction deviation values.

[0106] Among them, temperature sampling data represents the real-time temperature measurement value of the battery operating environment, including ambient temperature, battery surface temperature and internal temperature; temperature range distribution refers to the numerical range of temperature data divided according to a preset range, usually every 5℃ or 10℃ is a range; prediction deviation value refers to the difference between the model prediction value and the measured value; temperature range deviation data is used to represent the statistical characteristics of prediction error under different temperature ranges; temperature correction parameter refers to the model correction coefficient used to compensate for the influence of temperature.

[0107] Specifically, the battery energy management system continuously collects ambient temperature data through a network of temperature sensors distributed throughout the battery system. The system first preprocesses the collected temperature data, including outlier filtering and data smoothing. Then, it categorizes and statistically analyzes the temperature data according to preset temperature ranges, creating a temperature distribution histogram. For each temperature range, the system collects all prediction deviation data within that range and calculates statistical characteristics such as mean and standard deviation. Based on these statistical results, the system analyzes the correlation between temperature and prediction deviation, updating the temperature compensation parameters in the prediction model. Finally, the system uses the updated parameters to correct the original prediction deviation, improving prediction accuracy.

[0108] In practical applications, temperature compensation may encounter problems such as drastic temperature changes leading to unsatisfactory compensation effects. To address this issue, the battery energy management system employs a dynamic temperature compensation mechanism. Specifically, the system implements temperature change characteristic recognition: by analyzing the rate and pattern of temperature change, it identifies steady-state and transient temperature changes; establishes a dynamic impact model of temperature changes on prediction deviations; and dynamically adjusts the compensation strategy based on temperature change characteristics. The system also establishes a hierarchical compensation framework: a steady-state compensation model is used for slow temperature changes, while a transient compensation model is activated for rapid temperature changes. When a rapid temperature change is detected, the system initiates a special processing mechanism: increasing the temperature sampling frequency and shortening the compensation cycle; simultaneously considering the temperature hysteresis effect and introducing a time delay term into the compensation model. By establishing a temperature condition library and a corresponding compensation model library, the system achieves accurate compensation for various temperature change scenarios. For newly emerging temperature change patterns, the system initiates a self-learning mechanism to continuously optimize the compensation effect.

[0109] In this embodiment, an intelligent collaborative management method based on cruise mode is adopted. By monitoring current stability in real time, calibrating multi-dimensional parameters, and comparing and analyzing historical data, it can automatically and accurately assess battery health parameters during daily driving. This effectively solves the technical problems of traditional methods, such as the need for periodic offline testing, easy parameter drift, and low assessment accuracy. It eliminates additional maintenance and testing time, improving the user experience. Data acquisition and multi-dimensional analysis under steady-state conditions ensure the accuracy of the assessment results. Dynamic adjustment of charging and discharging strategies based on real-time assessment results and the establishment of a temperature correction model enable continuous optimization of the battery management system, extending battery life and improving vehicle safety. This intelligent collaborative management method provides a more efficient and reliable technical solution for battery management in new energy vehicles.

[0110] The battery energy management system in the embodiments of this invention is described below from the perspective of hardware processing. Please refer to [link / reference needed]. Figure 3 This is a schematic diagram of the physical device structure of a battery energy management system in an embodiment of this application.

[0111] It should be noted that, Figure 3 The structure of the battery energy management system shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0112] like Figure 3 As shown, the battery energy management system includes a CPU 301, which can perform various appropriate actions and processes according to a program stored in ROM 302 or a program loaded from storage section 308 into RAM 303, such as executing the methods described in the above embodiments. RAM 303 also stores various programs and data required for system operation. The CPU 301, ROM 302, and RAM 303 are interconnected via bus 304. I / O interface 305 is also connected to bus 304.

[0113] The following components are connected to I / O interface 305: input section 306 including audio input devices, push-button switches, etc.; output section 307 including liquid crystal display (LCD) and audio output devices, indicator lights, etc.; storage section 308 including hard disks, etc.; and communication section 309 including network interface cards such as LAN (Local Area Network) cards, modems, etc. Communication section 309 performs communication processing via a network such as the Internet. Drive 310 is also connected to I / O interface 305 as needed. Removable media 311, such as disks, optical disks, magneto-optical disks, semiconductor memories, etc., are installed on drive 310 as needed so that computer programs read from them can be installed into storage section 308 as needed.

[0114] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing computer programs for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 309, and / or installed from removable medium 311. When the computer program is executed by CPU 301, it performs the various functions defined in the present invention.

[0115] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. Each block in a flowchart or block diagram may represent a module, program segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those shown in the drawings.

[0116] Specifically, the battery energy management system of this embodiment includes a processor and a memory. The memory stores a computer program. When the computer program is executed by the processor, it implements the intelligent collaborative battery energy management method provided in the above embodiment.

[0117] In another aspect, the present invention also provides a computer-readable storage medium, which may be included in the battery energy management system described in the above embodiments; or it may exist independently and not assembled into the battery energy management system. The storage medium carries one or more computer programs that, when executed by a processor of the battery energy management system, cause the battery energy management system to implement the intelligent collaborative battery energy management method provided in the above embodiments.

[0118] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit it. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

[0119] As used in the above embodiments, depending on the context, the term "when..." can be interpreted as meaning "if...", "after...", "in response to determining...", or "in response to detecting...". Similarly, depending on the context, the phrase "when determining..." or "if (the stated condition or event) is interpreted as meaning "if determining...", "in response to determining...", "when (the stated condition or event) is detected", or "in response to detecting (the stated condition or event)".

Claims

1. A battery energy management method based on intelligent collaboration, characterized in that, Applied to a battery energy management system, the method includes: Receive cruise mode parameters sent by the vehicle control terminal; the cruise mode parameters include vehicle speed stability parameters and accelerator pedal position change rate; When the vehicle speed stability parameter is higher than the preset stability threshold and the accelerator pedal position change rate is lower than the preset position change threshold, the driving mode is determined to be the cruise mode that meets the calibration conditions, and the real-time current data of the vehicle battery is collected. The dispersion of the real-time current data within a statistical period is calculated to obtain the current stability index; When the current stability index is within a preset value range, the terminal voltage, branch current and temperature data of the vehicle battery are collected within a preset calibration window time to obtain a calibration dataset. Input the calibration dataset into the battery equivalent circuit model to obtain health feature parameters characterizing the current battery health status; The health characteristic parameters are compared with historical characteristic data in the battery management database over time to determine the rate of change of the health characteristic parameters. When the rate of change of the parameter is not higher than a preset mutation threshold, a battery health assessment result is generated based on the historical feature data and the health feature parameters. Based on the battery health assessment results, the control parameters of the battery charging and discharging strategy are adjusted, and the battery health prediction model for predicting the remaining battery life is updated.

2. The method of claim 1, wherein, After the step of inputting the calibration dataset into the battery equivalent circuit model to obtain health characteristic parameters characterizing the current battery health state, the method further includes: When the instantaneous rate of change of the battery output power is detected to be greater than or equal to the preset emergency threshold, the health characteristic parameters are temporarily stored and the current calibration process is marked as an abnormal interruption state. After the instantaneous rate of change recovers to below the preset emergency threshold, the abnormal duration of the abnormal interruption state is determined; When the duration of the abnormality is greater than or equal to a preset time threshold, the real-time current data of the vehicle battery is re-acquired.

3. The method of claim 2, wherein, After the step of determining the abnormal duration of the abnormal interruption state, the method further includes: When the duration of the abnormality is less than the preset time threshold, the temporarily stored health characteristic parameters are read. The health characteristic parameters are compared with historical characteristic data in the battery management database over time, and a battery health assessment result is generated based on the historical characteristic data and the health characteristic parameters.

4. The method of claim 1, wherein, After the steps of adjusting the control parameters of the battery charging and discharging strategy based on the battery health assessment results and updating the battery health prediction model for predicting the remaining battery life, the method further includes: Based on the adjusted control parameters and the updated battery health prediction model, the predicted battery performance values ​​for the future preset time period are calculated. During actual operation, the measured values ​​of battery performance are collected, and the predicted deviation between the predicted value of battery performance and the measured value of battery performance is calculated. When the predicted deviation value exceeds a preset deviation threshold, the model parameters of the battery health prediction model are corrected based on the predicted deviation value.

5. The method of claim 4, wherein, Before the step of correcting the model parameters of the battery health prediction model based on the prediction deviation value, the method further includes: Collect temperature sampling data of the environment in which the battery is located; The predicted deviation values ​​are categorized according to the interval distribution of the temperature sampling data to obtain temperature interval deviation data; Based on the temperature range deviation data, the temperature correction parameters of the battery health prediction model are updated, and the prediction deviation value is corrected.

6. A battery energy management system, characterized by, The battery energy management system includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code including computer instructions, and the one or more processors call the computer instructions to cause the battery energy management system to perform the method as described in any one of claims 1-5.

7. A computer-readable storage medium comprising instructions, characterized in that, When the instruction is executed on the battery energy management system, the battery energy management system performs the method as described in any one of claims 1-5.

8. A computer program product, characterized in that, When the computer program product is run on the battery energy management system, it causes the battery energy management system to perform the method as described in any one of claims 1-5.

Images