Battery peak power determination method and related equipment

Abstract

The embodiment of the invention provides a battery peak power determination method and related equipment, and belongs to the technical field of power batteries. According to the embodiment, the peak power value can be output through the peak power prediction model in combination with the real-time terminal voltage, the battery capacity, the total battery capacity and the battery capacity change value of the power battery, the peak power value of the battery is obtained after continuous use, the power of electric equipment using the power battery can be adjusted in time according to the peak power value, and the power utilization efficiency is improved. The power supply function of the power battery is maintained and the service life of the battery is prolonged.

Description

Technical Field

[0001] This application relates to the field of power battery technology, and in particular to a method and related equipment for determining battery peak power. Background Technology

[0002] Due to their high energy density, lightweight, rechargeable characteristics, and low self-discharge rate, power batteries are widely used in portable electronic devices, wearable devices, electric vehicles, commercial energy storage systems, aerospace, military, and many other fields, making them an ideal choice for various application scenarios. However, affected by factors such as cyclic charging and discharging, high temperature, overcharging, and over-discharging, the performance of power batteries will gradually deteriorate, accompanied by significant safety hazards.

[0003] A decline in the performance of a power battery may be accompanied by a decrease in various parameters, affecting the normal use of the power battery. Devices powered by the power battery may find it difficult to quickly determine the specific parameters of the power battery, potentially leading to insufficient power supply.

[0004] In summary, the technical problems existing in the relevant technologies need to be improved. Summary of the Invention

[0005] The main objective of this application is to propose a method and related equipment for determining the peak power of a battery, so as to confirm the specific battery parameters of the power battery after continuous use, so that the equipment can adjust the power supply strategy in a timely manner to maintain normal power supply.

[0006] To achieve the above objectives, one aspect of this application proposes a method for determining the peak power of a battery, the method comprising:

[0007] The operating data of the power battery during the current charging and discharging process is obtained, and the operating parameters of the power battery are determined using the operating data. The operating parameters include at least the terminal voltage, battery capacity, total battery capacity, and battery capacity change value of the power battery. The operating parameters are input into the peak power prediction model to obtain the peak power value of the power battery. The power prediction model is used to determine the peak power value of the power battery in the current charging and discharging process based on the mapping relationship between the input operating parameters and the peak power.

[0008] In some embodiments, the method further includes: obtaining a peak power prediction model; The peak power prediction model includes: The test data of the power battery during the cyclic charging and discharging process under different operating conditions are obtained. The test data includes terminal voltage, current value, battery capacity and peak power. Based on the test data, determine the battery capacity increment of the power battery; Using the Gaussian process regression algorithm, a peak power prediction model is established with the terminal voltage, the current value, the battery capacity, and the battery capacity increment as model inputs, and the peak power as model output.

[0009] In some embodiments, determining the battery capacity increment of the power battery based on the test data includes: Acquire test data during multiple charge-discharge cycles and determine adjacent test data during charge-discharge cycles adjacent to the current charge-discharge cycle; The battery capacity increment of the power battery is determined by using a five-point cubic smoothing algorithm combined with the adjacent test data.

[0010] In some embodiments, the covariance function of the peak power prediction model is a Matern 5 / 2 kernel function.

[0011] In some embodiments, the prior distribution of the peak power prediction model is a zero-mean Gaussian process.

[0012] In some embodiments, after establishing a peak power prediction model using a Gaussian process regression algorithm, with the terminal voltage, the current value, the battery capacity, and the battery capacity increment as model inputs, and the peak power as the model output, the method further includes: The performance of the trained prediction model should be evaluated, and the evaluation metrics should include at least the mean absolute error, mean relative error, and coefficient of determination.

[0013] To achieve the above objectives, another aspect of this application provides a battery peak power determination device, the device comprising: The acquisition module is used to acquire the operating data of the power battery during the current charging and discharging process, and use the operating data to determine the operating parameters of the power battery. The operating parameters include at least the terminal voltage, battery capacity, total battery capacity and battery capacity change value of the power battery. The determination module is used to input the operating parameters into the peak power prediction model and obtain the peak power value of the power battery. The power prediction model is used to determine the peak power value of the power battery in the current charging and discharging process based on the mapping relationship between the input operating parameters and the peak power.

[0014] To achieve the above objectives, another aspect of this application provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the method described above.

[0015] To achieve the above objectives, another aspect of the embodiments of this application proposes a computer-readable storage medium storing a computer program that, when executed by a processor, implements the methods described above.

[0016] To achieve the above objectives, another aspect of the embodiments of this application proposes a computer program product, including a computer program that, when executed by a processor, implements the aforementioned method.

[0017] The embodiments of this application include at least the following beneficial effects: This application provides a method, apparatus, electronic device, storage medium, and program product for determining battery peak power. This solution acquires the operating data of a power battery during the current charging and discharging process, and uses this data to determine the operating parameters of the power battery. These operating parameters include at least the battery's terminal voltage, battery capacity, total battery capacity, and battery capacity change value. The operating parameters are input into a peak power prediction model to obtain the peak power value of the power battery. The power prediction model is used to determine the peak power value of the power battery during the current charging and discharging process based on the mapping relationship between the input operating parameters and the peak power. This embodiment can combine the real-time terminal voltage, battery capacity, total battery capacity, and battery capacity change value of the power battery, and output the peak power value through the peak power prediction model. This achieves the acquisition of the battery's peak power value after continuous use. Electrical devices using the power battery can adjust their power in a timely manner according to the peak power value, maintaining the power supply function of the power battery and extending its service life. Attached Figure Description

[0018] Figure 1 This is a flowchart of the battery peak power determination method provided in the embodiments of this application; Figure 2 This is a flowchart of the model building method provided in the embodiments of this application; Figure 3 This is a schematic diagram of the peak power direction provided in an embodiment of this application; Figure 4 This is a prediction comparison diagram of the charging model provided in the embodiments of this application; Figure 5 This is a comparison chart of the predictions of the discharge model provided in the embodiments of this application; Figure 6 This is a schematic diagram of the battery peak power determination device provided in the embodiments of this application; Figure 7 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit it. In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with those of this application; they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this application as detailed in the appended claims.

[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0021] Before providing a detailed description of the embodiments of this application, some of the nouns and terms involved in the embodiments of this application will be explained first. The nouns and terms involved in the embodiments of this application are subject to the following interpretations.

[0022] 1) Peak Power (SOP): refers to the maximum power that a power battery can safely output (discharge) or input (charge) within a short period of time under specific operating conditions (such as specific SOC, temperature, aging state) and constraints (such as voltage limits, current limits, temperature limits).

[0023] 2) Incremental Capacity (IC): This refers to the change in battery capacity caused by a unit change in voltage, i.e., dQ / dV. It is obtained by differentiating the constant current charge-discharge curve of the battery. Its curve characteristics are extremely sensitive to the electrochemical reactions and aging state inside the battery.

[0024] 3) Gaussian Process Regression (GPR): A nonparametric probabilistic model based on Bayesian inference, used to solve nonlinear regression problems. It not only provides the predicted mean but also the prediction uncertainty (variance), and has excellent small-sample learning ability and generalization performance.

[0025] 4) Five-Point Cubic Smoothing Algorithm: A data smoothing method based on local polynomial fitting. It uses a point and two points before and after it, for a total of five points, to perform cubic polynomial fitting. The fitted value of the point is used to replace the original value, which can effectively filter out high-frequency noise.

[0026] 5) State of Health (SOH): This typically refers to the ratio of the battery's current maximum usable capacity to its rated capacity, and is a key indicator for measuring the degree of battery aging. In this application, the total battery capacity Cn is a direct reflection of the SOH.

[0027] In view of this, this application provides a method for determining battery peak power. This method fuses the capacity increment characteristics reflecting the internal aging dynamics of the battery with the apparent state parameters (voltage, capacity) of the battery operation to construct a high-information-density multidimensional feature vector. Then, using a Gaussian process regression algorithm with strong nonlinear fitting capabilities and inherent uncertainty quantification advantages, an accurate, robust, and interpretable mapping model from this fused feature to peak power is established. This method not only achieves high-precision prediction of peak power but also adapts to battery aging and provides prediction confidence intervals, greatly improving the safety, reliability, and intelligence level of the battery management system (BMS) in power boundary estimation.

[0028] The battery peak power determination method provided in this application relates to the field of power batteries. This method can be applied to a terminal, a server, or software running on either a terminal or a server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, or in-vehicle terminal, but is not limited to these. The server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server can also be a node server in a blockchain network. The software can be an application implementing the battery peak power determination method, but is not limited to the above forms.

[0029] This application can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics devices, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0030] Figure 1 This is an optional flowchart of the battery peak power determination method provided in the embodiments of this application. Figure 1 The method may include, but is not limited to, steps S101 to S102.

[0031] Step S101: Obtain the operating data of the power battery during the current charging and discharging process.

[0032] When it is necessary to predict the real-time peak power of the battery (e.g., when the vehicle requests rapid acceleration, energy recovery, or the system optimizes power distribution), the battery's operating data near the current moment is first acquired. This data is typically collected in real time by the BMS via sensors, including: Terminal voltage V: The voltage between the positive and negative terminals of the battery.

[0033] Current I: The current flowing through the battery; it is negative when charging and positive when discharging.

[0034] Cumulative capacity Q: This reflects the total amount of electricity discharged or charged by the power battery during this charge-discharge cycle, and is a direct measure of the current state of charge (SOC). Typically, the system maintains a baseline SOC point (such as a fully charged state) and integrates from this baseline.

[0035] At the same time, the system also needs to acquire or estimate a key parameter: Total battery capacity Cn: This refers to the maximum usable capacity of the battery under its current state of health. Cn is a core indicator for measuring the state of health (SOH) of the battery, and it decreases as the battery ages. There are several ways to obtain it: a) It can be obtained through regular full-charge and discharge capacity calibration tests; b) It can be estimated in real time using a data-driven online SOH estimation algorithm (e.g., using charging voltage curve characteristics, impedance spectrum characteristics, etc.); c) A degradation model is stored in the BMS, estimated based on cycle count, cumulative throughput, operating temperature history, etc. In this application, Cn is used as an important input feature to distinguish different aging stages of the battery.

[0036] Step S102: Input the operating parameters into the peak power prediction model and obtain the peak power value of the power battery. The power prediction model is used to determine the peak power value of the power battery in the current charging and discharging process based on the mapping relationship between the input operating parameters and the peak power.

[0037] In this embodiment, the specific calculation process for the peak power value includes: (1) Determine the battery capacity change value (i.e., capacity increment IC) using operating data. The capacity increment IC cannot be measured directly and must be calculated. However, directly using the current instantaneous ΔV and ΔQ to calculate IC is extremely noisy and meaningless. Therefore, the core of this step is to calculate and obtain the IC value corresponding to the current state (especially the current voltage V) based on recent (or adjacent) quasi-steady-state charge and discharge segment data.

[0038] In practice, one of the following strategies can be adopted: Real-time sliding window calculation: The BMS continuously caches voltage-capacity data pairs (V, Q) collected within a short time window (e.g., the past few minutes) under relatively stable charge / discharge conditions (e.g., rates less than 0.5C). When prediction is needed, a local IC curve is calculated using the data within this window and a numerical differentiation method (e.g., the central difference method). Then, based on the current voltage V, the corresponding IC value is found on this local IC curve through interpolation.

[0039] Historical Feature Map Query: During the offline phase or when the battery is at rest, a complete and smooth IC curve is obtained by performing a standard charge-discharge test at a low rate (e.g., C / 3), and this curve is stored in memory as the "feature fingerprint" of the battery at the current State of Health (SOH). During online prediction, the corresponding IC value is obtained by querying or interpolating from the stored IC curve based on the current voltage V and the current total capacity Cn (used to index feature maps of different aging stages). This method is highly accurate but requires periodic updates to the feature map.

[0040] The specific calculation of numerical differentiation: For a discrete data point sequence {(Vi, Qi)}, the capacity increment IC_i at point i can be approximately calculated using the central difference formula.

[0041] To obtain more stable features, the original calculated IC sequence needs to undergo a further smoothing process.

[0042] (2) Perform smoothing filtering on the battery capacity change value.

[0043] The original IC sequence obtained from calculations typically contains a large amount of high-frequency noise caused by measurement noise and small current fluctuations, which can seriously affect the stability and accuracy of subsequent models. Therefore, this application employs a five-point cubic smoothing algorithm to filter the sequence. This algorithm is a low-pass filter that can effectively smooth random fluctuations while preserving the overall trend and key peak and valley characteristics of the IC curve.

[0044] Algorithm implementation: Given the original IC sequence, i = 1, 2, ..., N. The smoothed sequence is calculated according to the following rules: (1) For i=3, 4, ..., N-2, This is the original capacity increment sequence. ’ This is the smoothed result.

[0045] For boundary points (i=1,2,N-1,N), the mirror method, preserving the original value, or using a smoothing formula with fewer points can be used for processing.

[0046] (3) Construct the input feature vector.

[0047] The parameters are combined into a multidimensional feature vector X, which serves as the input to the prediction model. The feature set determined in this application is: X = [Cn, Q, V, IC](2) Cn represents the total battery capacity, Q represents the discharge or charge capacity, V represents the battery port voltage, which is a direct constraint on peak power, and IC represents the characteristic value of battery capacity increment.

[0048] This feature construction method achieves deep integration of macroscopic operating parameters and microscopic aging characteristics, providing the model with comprehensive and highly discriminative information input.

[0049] (4) Input the input feature vector into the peak power prediction model to obtain the peak power prediction value and uncertainty.

[0050] The peak power prediction model constructed in this application is trained based on the Gaussian process regression algorithm. This model has been pre-trained and integrated into the BMS software. The appropriate model (charging SOP model or discharging SOP model) is selected based on whether the current process is charging or discharging.

[0051] Inputting the feature vector X into the selected model, the model outputs not only the predicted mean of the peak power. (i.e., the most likely SOP value), and will also output the predicted variance σ² (or standard deviation σ).

[0052] Forecast Mean It provides a point estimate of the peak power.

[0053] Prediction variance σ²: quantifies the uncertainty of this estimate. The uncertainty stems from: a) The coverage density of the training data in the current input feature space region; b) Observation noise; c) The cognitive limitations of the model itself.

[0054] Confidence Interval: A confidence interval can be constructed. For example, a 95% confidence interval is [ - 1.96σ, +1.96σ]. This provides crucial safety boundary information for the BMS. A wide confidence interval indicates that the model has low predictive power for the state, and the BMS can use a more conservative power limit.

[0055] The peak power prediction values ​​obtained above The power supply (and its confidence interval) is output to the upper-level controller (such as the vehicle control unit (VCU), energy storage converter (PCS) controller, etc.). The controller integrates this information with factors such as temperature limits and lifespan considerations to ultimately determine and execute a safe and optimized power command. For example, during rapid acceleration of an electric vehicle, the VCU uses the predicted peak discharge power of the battery as an important input to determine the upper limit of the motor torque request.

[0056] To ensure the long-term effectiveness of the model, its performance can be evaluated periodically. When vehicles return to service stations or energy storage systems undergo maintenance, standard HPPC tests can be performed to obtain new (SOP_true, X) data pairs as the test set. Metrics such as the mean absolute error (MAE), mean relative error (MRE), and coefficient of determination (R²) between the model's predicted and actual values ​​are calculated. If performance degrades significantly (e.g., R² below 0.95, MRE greater than 3%), a model update process is triggered, retraining the model using a mix of old and new data to track the battery's aging trajectory.

[0057] Figure 2This is a flowchart illustrating the specific construction method of the peak power prediction model in this embodiment. This embodiment details how to obtain the peak power prediction model. Model construction is typically completed in a laboratory or cloud environment, and then the trained model parameters are deployed to the terminal BMS.

[0058] Step S201: Obtain test data of the power battery during cyclic charging and discharging under different operating conditions.

[0059] For the target type of power battery (such as NCM ternary lithium battery and LFP lithium iron phosphate battery), a series of experiments were designed and executed to collect test data covering the entire life cycle and multiple operating conditions. An example of the experimental design is as follows: Aging cycle test: At multiple constant temperature points, standard charge-discharge cycle aging (such as 1C charge-discharge) is performed on multiple groups of batteries of the same model to simulate capacity decay in actual use.

[0060] Characteristic and power test cycles: After a certain number of aging cycles (e.g., every 50 cycles), pause aging and perform the following tests: a. Capacity calibration: Perform constant current and constant voltage charging and constant current discharging at standard temperature, and record the complete (V, Q) curves for calculating the total capacity Cn and subsequent IC curves.

[0061] b. Peak power test (e.g., HPPC test): At multiple preset SOC points (e.g., 100%, 90%, ..., 10%), perform short-duration (e.g., 10 seconds) high-current pulse discharge and charge cycles. Record the pulse start voltage, pulse current, and pulse end voltage. A schematic diagram of the peak power is shown below. Figure 3 As shown.

[0062] Data logging: Throughout the test, terminal voltage V, current I, cumulative capacity Q, time t, and ambient temperature T are recorded synchronously at high frequency. Ultimately, each test point will be associated with a set of data: {Cn, Q, V, I, SOP T, number of cycles}.

[0063] Step S202: Determine the battery capacity increment of the power battery based on the test data.

[0064] The low-rate charge-discharge (V, Q) curves obtained from each capacity calibration test in step S201 are smoothed to obtain a smooth IC curve corresponding to this test. For each peak power test point, based on its voltage V, the corresponding IC value is found on the IC curve obtained from this calibration test through linear interpolation.

[0065] Step S203: Using the Gaussian process regression algorithm, a peak power prediction model is established with terminal voltage, current value, battery capacity and battery capacity increment as model inputs and peak power as model output.

[0066] (1) Constructing the training dataset: For the charging and discharging sample sets respectively: Input features Xi = [Cni, Qi, Vi, ICi] Output label yi = SOPi All samples are randomly shuffled and divided into training, validation, and test sets in a ratio (e.g., 7:2:1). The training set is used for model parameter learning, the validation set is used for hyperparameter tuning and early stopping, and the test set is used for final performance evaluation.

[0067] (2) Use the Gaussian process regression algorithm to establish a prediction model.

[0068] Train a separate GPR model for each of the charging and discharging data. Taking the training of the charging model as an example: Model definition: Assume that the unknown function f(X) between peak power SOP and input features X follows a Gaussian process prior: (3) The mean function m(X) is typically set to a zero-mean function (zero-mean assumption). The covariance function is chosen as the Matern 5 / 2 kernel function, which has the following form: (4) Where r is the Euclidean distance between input vectors, l is the length scale parameter, and σf is the signal amplitude parameter. Additionally, the model includes an observation noise variance parameter σn².

[0069] Optimize the kernel function parameters r, l, σ using the sample set (X, SOP). f The posterior distribution is obtained as follows: (5) And calculate the predicted mean As a result of peak power prediction.

[0070] in: It is Gaussian noise. ; Let be the sample input vector, describing the input feature vector of the j-th data point in the training set; Let be the sample input vector, describing the input feature vector of the j-th data point in the training set; The covariance function (Matern5 / 2 kernel) describes the two input vectors. and A function of similarity between them; σ f is the signal amplitude, used to control the magnitude or variance of the function f(x); r =||xi - yi||, describing the Euclidean distance between input vectors; l is the scale parameter, used to control the length scale of the decay rate of the covariance function; Let be the peak power random variable to be predicted, representing the model's performance on a given input. The predicted output is a random variable that follows a Gaussian distribution; It is a prediction The mean of the peak power, i.e., the point estimate of the peak power; Predicting random variables The covariance matrix represents the uncertainty or confidence interval of the prediction; The input feature vector of the sample to be predicted Given a training set, the goal of training is to find an optimal set of hyperparameters that maximizes the marginal likelihood of the training data. This process can be achieved using optimization algorithms such as gradient descent, conjugate gradient, or quasi-Newton's method.

[0071] Repeat the above process on the discharge dataset to obtain an independent discharge GPR model. The charging and discharging models have the same structure, but due to differences in data distribution and underlying mechanisms, the learned hyperparameters θ are different.

[0072] (3) Evaluate the performance of the trained prediction model.

[0073] The model performance is evaluated using a separate test set. For each sample in the test set, given the input feature X, the model outputs the predicted mean. and prediction variance σ ².

[0074] The evaluation metrics include: mean absolute error, mean relative error, and coefficient of determination R². The coefficient of determination measures the extent to which the model explains the variation in the data, and the closer it is to 1, the better.

[0075] The method described in this application achieves the following results in typical tests: MRE prediction for charging SOP < 1.5%, MRE prediction for discharging SOP < 1%, and R² > 0.99, demonstrating extremely high accuracy.

[0076] (4) The evaluated and performance-compliant charging and discharging GPR model (i.e., its optimal hyperparameter θ and partial information of the training data, depending on the specific implementation) is solidified into a software module or parameter file and integrated into the software system of the target BMS to complete the deployment.

[0077] Experimental test results are as follows Figure 4 , Figure 5As shown, the model's predicted curve closely matches the actual measured values. Specific error results are as follows: Mean Absolute Error (MAE) of the charging model: 13.8487 W, Mean Relative Error (MRE): 1.35%, Goodness of Fit (GFA)... 2 ): 0.9984. Discharge model MAE: 26.8785 W, MRE: 0.91%. 2 The accuracy is 0.9956. This method can maintain high prediction accuracy and stability even with a small sample size and the presence of noise, providing a highly robust modeling approach for predicting the peak power of power batteries.

[0078] Please see Figure 6 This application also provides a battery peak power determination device that can implement the above method. The device includes: The acquisition module 61 is used to acquire the operating data of the power battery during the current charging and discharging process, and use the operating data to determine the operating parameters of the power battery. The operating parameters include at least the terminal voltage, battery capacity, total battery capacity and battery capacity change value of the power battery. The determination module 62 is used to input the operating parameters into the peak power prediction model and obtain the peak power value of the power battery. The power prediction model is used to determine the peak power value of the power battery in the current charging and discharging process based on the mapping relationship between the input operating parameters and the peak power.

[0079] In some embodiments, the apparatus further includes a training module for: The test data of the power battery during the cyclic charging and discharging process under different operating conditions are obtained. The test data includes terminal voltage, current value, battery capacity and peak power. Based on the test data, determine the battery capacity increment of the power battery; Using the Gaussian process regression algorithm, a peak power prediction model is established with the terminal voltage, the current value, the battery capacity, and the battery capacity increment as model inputs, and the peak power as model output.

[0080] In some embodiments, determining the battery capacity increment of the power battery based on the test data includes: Acquire test data during multiple charge-discharge cycles and determine adjacent test data during charge-discharge cycles adjacent to the current charge-discharge cycle; The battery capacity increment of the power battery is determined by using a five-point cubic smoothing algorithm combined with the adjacent test data.

[0081] In some embodiments, the covariance function of the peak power prediction model is a Matern 5 / 2 kernel function.

[0082] In some embodiments, the prior distribution of the peak power prediction model is a zero-mean Gaussian process.

[0083] In some embodiments, after establishing a peak power prediction model using a Gaussian process regression algorithm, with the terminal voltage, the current value, the battery capacity, and the battery capacity increment as model inputs, and the peak power as the model output, the method further includes: The performance of the trained prediction model should be evaluated, and the evaluation metrics should include at least the mean absolute error, mean relative error, and coefficient of determination.

[0084] It is understood that the content of the above method embodiments is applicable to the present device embodiments. The specific functions implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0085] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described method. This electronic device can be any smart terminal, including tablet computers, in-vehicle computers, etc.

[0086] It is understood that the content of the above method embodiments is applicable to this device embodiment. The specific functions implemented by this device embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0087] Please see Figure 7 , Figure 7 The hardware structure of an electronic device according to another embodiment is illustrated. The electronic device includes: The processor 701 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application. The memory 702 can be implemented as a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 702 can store the operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 702 and is called and executed by the processor 701 using the methods described in the embodiments of this application. The input / output interface 703 is used to implement information input and output; The communication interface 704 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.). Bus 705 transmits information between various components of the device (e.g., processor 701, memory 702, input / output interface 703, and communication interface 704); The processor 701, memory 702, input / output interface 703, and communication interface 704 are connected to each other within the device via bus 705.

[0088] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method.

[0089] It is understood that the content of the above method embodiments is applicable to this storage medium embodiment. The specific functions implemented in this storage medium embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0090] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0091] It is understood that the content of the above method embodiments is applicable to the embodiments of this program product. The specific functions implemented by the embodiments of this program product are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0092] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0093] The battery peak power determination method, apparatus, electronic device, storage medium, and program product provided in this application acquire operating data of the power battery during the current charging and discharging process. This data is used to determine the operating parameters of the power battery, including at least the battery's terminal voltage, battery capacity, total battery capacity, and battery capacity change. The operating parameters are input into a peak power prediction model to obtain the peak power value of the power battery. The power prediction model determines the peak power value of the power battery during the current charging and discharging process based on the mapping relationship between the input operating parameters and the peak power. This embodiment can combine the real-time terminal voltage, battery capacity, total battery capacity, and battery capacity change of the power battery, and output the peak power value through the peak power prediction model. This allows for the acquisition of the battery's peak power value after continuous use. Devices using the power battery can adjust their power output in a timely manner based on the peak power value to maintain the power supply function of the power battery and extend its service life.

[0094] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0095] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0096] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0097] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or appropriate combinations thereof.

[0098] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0099] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0100] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0101] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0102] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0103] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0104] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A method for determining the peak power of a battery, characterized in that, The method includes: The operating data of the power battery during the current charging and discharging process is obtained, and the operating parameters of the power battery are determined using the operating data. The operating parameters include at least the terminal voltage, battery capacity, total battery capacity, and battery capacity change value of the power battery. The operating parameters are input into the peak power prediction model to obtain the peak power value of the power battery. The power prediction model is used to determine the peak power value of the power battery in the current charging and discharging process based on the mapping relationship between the input operating parameters and the peak power.

2. The method according to claim 1, characterized in that, The method further includes: obtaining a peak power prediction model; The peak power prediction model includes: The test data of the power battery during the cyclic charging and discharging process under different operating conditions are obtained. The test data includes terminal voltage, current value, battery capacity and peak power. Based on the test data, determine the battery capacity increment of the power battery; Using the Gaussian process regression algorithm, a peak power prediction model is established with the terminal voltage, the current value, the battery capacity, and the battery capacity increment as model inputs, and the peak power as model output.

3. The method according to claim 2, characterized in that, The step of determining the battery capacity increment of the power battery based on the test data includes: Acquire test data during multiple charge-discharge cycles and determine adjacent test data during charge-discharge cycles adjacent to the current charge-discharge cycle; The battery capacity increment of the power battery is determined by using a five-point cubic smoothing algorithm combined with the adjacent test data.

4. The method according to claim 2, characterized in that, The covariance function of the peak power prediction model is the Matern 5 / 2 kernel function.

5. The method according to claim 2, characterized in that, The prior distribution of the peak power prediction model is a zero-mean Gaussian process.

6. The method according to claim 2, characterized in that, After establishing a peak power prediction model using the Gaussian process regression algorithm, with the terminal voltage, the current value, the battery capacity, and the battery capacity increment as model inputs, and the peak power as the model output, the method further includes: The performance of the trained prediction model should be evaluated, and the evaluation metrics should include at least the mean absolute error, mean relative error, and coefficient of determination.

7. A battery peak power determination device, characterized in that, The device includes: The acquisition module is used to acquire the operating data of the power battery during the current charging and discharging process, and use the operating data to determine the operating parameters of the power battery. The operating parameters include at least the terminal voltage, battery capacity, total battery capacity and battery capacity change value of the power battery. The determination module is used to input the operating parameters into the peak power prediction model and obtain the peak power value of the power battery. The power prediction model is used to determine the peak power value of the power battery in the current charging and discharging process based on the mapping relationship between the input operating parameters and the peak power.

8. An electronic device, characterized in that, The electronic device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the method according to any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 6.

Images