Method, device and equipment for estimating power battery status of sweeping vehicle

Abstract

The present invention relates to a method, device and equipment for estimating the state of a power battery of a sweeper. The method: collects impedance characteristics of the power battery of the sweeper under various working conditions, and obtains battery working condition characteristic data by measuring a random low-frequency modulated multi-sinusoidal excitation signal; performs fitting operation through an equivalent circuit model to obtain a battery health factor model; performs charging process feature extraction and analysis to obtain a battery charging curve reconstruction model; performs extended Kalman filtering operation to obtain a battery state of charge value; performs segmented processing and Gaussian process regression calculation on the voltage and current data during the charging process to obtain a battery health state value; updates the polynomial mapping coefficients of the battery health factor model and the weight parameters of the battery charging curve reconstruction model to obtain a target health factor model and a target charging curve reconstruction model. The implementation of the present invention ensures the adaptability and accuracy of the state estimation method throughout the entire life cycle of the battery.

Description

Technical Field

[0001] The present invention relates to the technical field of power batteries, and in particular to a method, device and equipment for estimating the state of a power battery of a sweeper. Background Art

[0002] Traditional battery state estimation methods are primarily designed for fixed operating conditions, such as electric vehicles. They struggle to meet the demands of specialized operating conditions, such as the frequent starts and stops and drastic load fluctuations experienced by sweepers. In actual operation, the complex working environment and changing operating modes of sweepers lead to nonlinear and time-varying battery charge and discharge characteristics, posing significant challenges to accurate battery state estimation.

[0003] In practical applications, sweeper vehicle power batteries face challenges such as incomplete charging processes and difficulty measuring impedance characteristics. Firstly, due to the random and continuous nature of sweeper operations, complete charging process data is often unavailable, making traditional health assessment methods based on standard charging curves difficult to apply. Secondly, complex operating environments cause the battery's internal impedance characteristics to exhibit significant nonlinearity and time-varying characteristics, making it difficult to accurately capture impedance characteristics using traditional impedance measurement methods. Summary of the Invention

[0004] The main purpose of the present invention is to provide a method, device and equipment for estimating the state of a power battery of a sweeper. The present invention ensures the adaptability and accuracy of the state estimation method throughout the entire life cycle of the battery.

[0005] To achieve the above object, the present invention provides a method for estimating the state of a power battery of a sweeper, comprising the following steps:

[0006] The impedance characteristics of the sweeper's power battery are collected under various operating conditions, and the battery operating condition characteristic data is obtained by measuring the random low-frequency modulated multi-sine excitation signal.

[0007] According to the battery operating condition characteristic data, a fitting operation is performed through an equivalent circuit model, and a polynomial mapping relationship between the health factor and the capacity and coulombic efficiency is established to obtain a battery health factor model;

[0008] Based on the charging data in the battery operating condition characteristic data, performing charging process feature extraction and analysis to obtain a battery charging curve reconstruction model;

[0009] Performing an extended Kalman filter operation on the polynomial mapping relationship in the battery health factor model to obtain a battery state of charge value;

[0010] Based on the battery charging curve reconstruction model, the voltage and current data during the charging process are processed in segments and Gaussian process regression is performed to obtain the battery health status value;

[0011] According to the battery state of charge value and the battery state of health value, the polynomial mapping coefficients of the battery health factor model and the weight parameters of the battery charging curve reconstruction model are updated to obtain a target health factor model and a target charging curve reconstruction model.

[0012] The present invention also provides a device for estimating the state of a power battery of a sweeper, comprising:

[0013] The acquisition module is used to collect the impedance characteristics of the sweeper's power battery under various working conditions, and obtain the battery operating condition characteristic data by measuring the random low-frequency modulated multi-sinusoidal excitation signal;

[0014] Establishing a module for performing a fitting operation through an equivalent circuit model based on the battery operating condition characteristic data, and establishing a polynomial mapping relationship between the health factor and the capacity and coulomb efficiency to obtain a battery health factor model;

[0015] An analysis module, configured to extract and analyze charging process characteristics based on the charging data in the battery operating condition characteristic data to obtain a battery charging curve reconstruction model;

[0016] an operation module, configured to perform an extended Kalman filter operation on the polynomial mapping relationship in the battery health factor model to obtain a battery state of charge value;

[0017] a processing module, configured to reconstruct a model based on the battery charging curve, perform segmented processing and Gaussian process regression calculation on the voltage and current data during the charging process, and obtain a battery health status value;

[0018] An updating module is used to update the polynomial mapping coefficients of the battery health factor model and the weight parameters of the battery charging curve reconstruction model according to the battery state of charge value and the battery health state value to obtain a target health factor model and a target charging curve reconstruction model.

[0019] The present invention also provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the above methods when executing the computer program.

[0020] The present invention also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of any of the above methods are implemented.

[0021] In summary, the technical solution provided by the present invention effectively solves the problem of accuracy of battery impedance measurement under sweeper working conditions by adopting random low-frequency modulated multi-sinusoidal excitation signals for impedance feature acquisition, and the obtained impedance feature data is more reliable; a health factor model is constructed based on the equivalent circuit model and polynomial mapping relationship, which accurately describes the attenuation characteristics of battery capacity and Coulomb efficiency, and the battery state evaluation is more comprehensive; the extreme learning machine combined with genetic algorithm and hill climbing optimization realizes the reconstruction of the charging curve, effectively solves the problem of incomplete charging data, and improves the robustness of state estimation; the extended Kalman filter algorithm is used to perform online estimation of the battery state of charge, which significantly reduces the estimation error and ensures the reliability of the results; accurate evaluation of the battery health state is achieved through Gaussian process regression, and probability correction is performed in combination with Bayesian theory to improve the accuracy of the evaluation results; a dynamic update mechanism for model parameters is established to ensure the adaptability and accuracy of the state estimation method throughout the battery life cycle. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 This is a schematic diagram of the steps of a method for estimating the power battery status of a sweeping vehicle according to one embodiment of the present invention;

[0023] Figure 2 This is a structural block diagram of a power battery state estimation device for a sweeping vehicle according to one embodiment of the present invention;

[0024] Figure 3 It is a schematic block diagram of the structure of a computer device according to an embodiment of the present invention.

[0025] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0027] Reference Figure 1 This embodiment provides a method for estimating the state of a power battery of a sweeper, comprising the following steps:

[0028] S1, collects impedance characteristics of the sweeper's power battery under various operating conditions, and obtains battery operating condition characteristic data by measuring a random low-frequency modulated multi-sine excitation signal;

[0029] The voltage and current data of the sweeper's power battery were sampled under low-speed sweeping, medium-speed sweeping, high-speed sweeping, no-load driving, loaded driving, and a combination of operating conditions to obtain raw operating data. The start-stop frequency in the raw operating data was statistically calculated to analyze the battery's load variation characteristics under each operating condition. This analysis process yielded characteristic operating parameters, such as the battery's load response characteristics and charge-discharge cycle under different operating conditions. Based on these characteristic operating parameters, the excitation amplitude of the random low-frequency modulated multi-sine excitation signal was set, and the frequency range of the excitation signal was set from 0.01Hz to 1000Hz to generate the target excitation signal. This frequency range covers the battery's dynamic response frequency band under different operating conditions and can fully stimulate the battery's internal resistance characteristics. The target excitation signal was applied to the power battery. The excitation signal caused the battery's internal voltage and current to respond, and the battery's voltage and current response data under each operating condition were collected. This response data generates impedance measurement data, reflecting the battery's electrochemical behavior under different excitation frequencies, including key parameters such as the battery's resistance and polarization characteristics. Using this impedance measurement data, the battery's different internal resistance components are separated and calculated, including ohmic internal resistance, electrochemical polarization internal resistance, and concentration polarization internal resistance. Each type of internal resistance reflects the battery's physical and electrochemical characteristics under different operating conditions. Based on the characteristic impedance parameters, the battery's internal resistance trends under different operating conditions are analyzed. Changes in internal resistance are closely related to battery aging, capacity degradation, and changes in internal chemical reactions. By analyzing the internal resistance trends, impedance variation characteristic data is generated, helping to determine the battery's health and future performance degradation. The original operating condition data, operating condition characteristic parameters, impedance measurement data, and impedance variation characteristic data are fused to generate battery operating condition characteristic data.

[0030] S2, based on the battery operating condition characteristic data, performs fitting calculations through an equivalent circuit model, and establishes a polynomial mapping relationship between the health factor and the capacity and coulomb efficiency to obtain a battery health factor model;

[0031] Specifically, based on the battery operating condition characteristic data, a Laplace transform is performed on the voltage and current responses of the battery equivalent circuit model to obtain the battery's s-domain transfer function parameter set. The Laplace transform converts the battery's complex responses in the time domain to the frequency domain, enabling a more concise and systematic representation of the battery's voltage and current responses, thereby extracting the battery's dynamic characteristics under various operating conditions. A nonlinear least-squares fit is performed based on the s-domain transfer function parameter set to obtain key parameters in the battery equivalent circuit model, such as the ohmic internal resistance parameter, electrochemical polarization RC network parameters, and concentration polarization RC network parameters. The battery's equivalent circuit model consists of resistors, capacitors, and inductors, describing the battery's electrical characteristics and electrochemical reaction processes. At this stage, the fitting process aims to determine the battery's internal resistance parameter matrix, which represents the impedance characteristics of the battery at different frequencies and operating conditions. Through nonlinear least-squares fitting, model errors are effectively reduced, resulting in more accurate battery internal resistance parameters. A least-squares fit is performed to determine the relationship between each parameter in the battery internal resistance parameter matrix and the number of battery cycles. A battery's internal resistance decays with increasing cycle count. By fitting the relationship between battery internal resistance parameters and cycle count, a set of internal resistance decay characteristic curves is derived, reflecting the battery's performance degradation over time and under different operating conditions. By analyzing these internal resistance decay characteristic curves, the aging mechanism and performance degradation patterns of the battery can be understood. Based on the set of internal resistance decay characteristic curves, a capacity decay polynomial model is constructed, and a set of capacity decay coefficients is calculated. Capacity decay is a key indicator of battery aging and is closely related to changes in internal resistance. Polynomial modeling describes the decay of battery capacity with time and usage, deriving a mathematical expression for capacity decay. Furthermore, based on the set of internal resistance decay characteristic curves, a polynomial model for coulombic efficiency decay is constructed, and a set of coulombic efficiency coefficients is calculated. Coulombic efficiency is a key parameter in the battery charging and discharging process, and its decay is also a reflection of battery aging. By establishing a coulombic efficiency decay model, the efficiency loss of the battery over long-term use can be accurately predicted. The capacity decay mapping function and the coulombic efficiency mapping function are weighted and combined to construct an initial battery health factor model. To improve the accuracy of the battery health factor model, the model is optimized. A five-fold cross-validation was performed on the weight coefficients of the initial battery health factor model. Cross-validation is a model validation method that effectively avoids overfitting and improves the model's generalization ability. The validation error threshold ε was set to 0.01, and iterative optimization was performed by minimizing the root mean square error (RMSE). The model's weight coefficients were adjusted to make the model's predictions more closely aligned with the actual battery health status. The iterative optimization process reduces model error by adjusting the weight coefficients, ensuring that the model can provide accurate health factor predictions under various operating conditions. After iterative optimization and weight adjustment, the optimal set of weight coefficients was obtained, and the parameters of the initial battery health factor model were updated based on the optimal coefficients to obtain the battery health factor model.

[0032] S3, based on the charging data in the battery operating condition characteristic data, performing charging process feature extraction and analysis to obtain a battery charging curve reconstruction model;

[0033] It should be noted that the charging data is segmented. Voltage and current changes occur in distinct phases, such as the charging start phase, constant current phase, constant voltage phase, and charging termination phase. By analyzing the characteristics of the voltage rise rate and current change rate in the charging data, the charging process is divided into different phases, generating a segmented charging feature data matrix. The data for each phase represents different characteristics of the charging process. Based on this segmented charging feature data matrix, a genetic algorithm is used to extract features from the charging data for each phase. A genetic algorithm is an optimization method that can find the global optimal solution in a complex search space. The goal of the genetic algorithm is to extract the most representative voltage and current feature points from the voltage and current data for each charging phase. These feature points can comprehensively reflect the key changes in the charging process. The genetic algorithm optimizes the selection of feature points to ensure that the selected feature points effectively represent the overall characteristics of the charging process, forming a feature point set. Feature vectors are then constructed from this feature point set. The voltage and current feature vectors contain information about the voltage and current changes, respectively, for each charging phase, representing the electrical characteristics of the battery during charging. The voltage and current feature vectors are combined into a training sample set to form the input data matrix for the extreme learning machine. Based on the constructed input data matrix, an extreme learning machine network structure with L hidden nodes is constructed. Extreme learning machines are a fast and efficient training method for neural networks. This method maps the input data matrix to an output space with nonlinear relationships, enabling accurate modeling of the charging curve. After constructing the network structure, the input weights and bias parameters of the extreme learning machine are optimized using a hill climbing algorithm. This algorithm is a local search algorithm that iteratively optimizes the weights and bias parameters to better fit the network to the charging data, thereby improving the model's predictive capabilities. Based on the initial set of network parameters, the output weights of the extreme learning machine are analytically solved. Based on the network's input and output relationships, a charging curve mapping model is derived. This model can predict the charging curve characteristics based on the input voltage and current characteristic points. The error between the predictions of the charging curve mapping model and the actual charging curve is calculated. By comparing the difference between the predicted results and the actual charging curve, a model evaluation metric is obtained to measure the model's prediction accuracy. Based on the model evaluation metric, iterative optimization is performed to adjust the network parameters to obtain the optimal set of network parameters. This optimization process minimizes the error, improving the model's accuracy and generalization under different charging conditions. During the optimization process, the model's predictive capabilities are continuously enhanced by adjusting parameters such as weights and biases. When the error reaches a predetermined threshold, the model is considered optimal. Based on the optimal set of network parameters, the parameters of the charging curve mapping model are updated, ultimately resulting in a battery charging curve reconstruction model.

[0034] S4, performing an extended Kalman filter operation on the polynomial mapping relationship in the battery health factor model to obtain a battery state of charge value;

[0035] Specifically, the actual capacity value is obtained by calculating parameters based on the capacity decay mapping function in the battery health factor model. The capacity decay mapping function reflects the decay of battery capacity over time and usage. By calculating the parameters of this mapping function, the current actual capacity value of the battery is obtained. Similarly, the coulombic efficiency mapping function in the battery health factor model is used to calculate parameters to obtain the coulombic efficiency value. Coulombic efficiency is related to the energy conversion efficiency during the battery's charge and discharge processes and reflects the battery's energy utilization efficiency during cycling. Based on the actual capacity and coulombic efficiency values, the battery's state-space equation is constructed. The state-space equation describes the dynamic behavior of a system in the time domain and includes state variables and state transition equations. In the case of batteries, state variables include state of charge (SOC), internal resistance, and capacity, while the state transition equations describe how these variables change over time. By incorporating the effects of capacity decay and coulombic efficiency, the battery's state-space equation is constructed. Furthermore, the nonlinear relationship between the battery's terminal voltage and SOC is modeled. The battery's terminal voltage and SOC have a complex nonlinear relationship, especially during charge and discharge, where the voltage exhibits different curves as the SOC changes. Through nonlinear modeling, the relationship between battery terminal voltage and state of charge is more accurately reflected, resulting in an observation equation model. Based on the state equation model and the observation equation model, an extended Kalman filter is performed. In the extended Kalman filter, a state prediction value and an error covariance matrix are calculated. The state prediction value is the state predicted at the next moment based on previous state information and the system's state equation, while the error covariance matrix describes the uncertainty of the prediction value. During the prediction process, a priori state variables are calculated based on the previous state variables and the state transition equation. The state variables represent the optimal estimate of the system in the absence of new measurement information. The error covariance matrix provides quantitative information on the accuracy of the prediction value, reflecting the model's prediction error and uncertainty. Based on the a priori state variables and the observation equation model, combined with actual battery measurement data, the filter gain coefficient is calculated by calculating the Kalman gain matrix. The Kalman gain matrix is the core component of the Kalman filter and determines the weighting ratio between the predicted and observed values. In the extended Kalman filter, the Kalman gain coefficient effectively balances the difference between the predicted and actual measured values, ensuring that the final filter result both reflects the dynamic changes of the system and effectively corrects for measurement errors. Based on the filter gain coefficient, the predicted state value is corrected to obtain the a posteriori state variable. This a posteriori state variable represents the final estimate of the battery state based on the existing predicted value and actual observed data. By combining the a priori state variable with the measured data, the Kalman filter accurately updates and corrects the battery's state of charge. After each filtering cycle, the error covariance matrix is updated based on the a posteriori state variable. Through the iterative process of the extended Kalman filter, the battery's state of charge value is obtained.

[0036] S5, based on the battery charging curve reconstruction model, performs segmented processing and Gaussian process regression calculation on the voltage and current data during the charging process to obtain the battery health status value;

[0037] The battery's voltage and current curves are segmented based on the charging data output by the battery charging curve reconstruction model. The charging process is divided into multiple stages, such as the constant current stage and the constant voltage stage. The voltage and current variation characteristics of each stage exhibit distinct patterns. Segmenting the voltage and current curves according to the different stages of the charging process yields more detailed stage-by-stage data. The voltage and current data from the segmented charging stage data are integrated to calculate the charging duration and charging capacity parameters for each stage. The charging capacity parameter reflects the energy stored in the battery during a given stage, while the charging duration indicates the duration of the battery's charge during that stage. These parameters quantify the battery's energy accumulation and the duration of the charging process. Based on the voltage sequence in the segmented charging stage data, the voltage difference between adjacent sampling points is calculated and divided by the sampling interval to obtain the voltage change rate parameter. The voltage change rate reflects the dynamic changes in the battery during the charging process. Excessively rapid or slow voltage changes indicate battery abnormalities, such as increased internal resistance or capacity decay. The charging capacity, charging time, and voltage change rate parameters are combined to construct a training sample matrix, which serves as input data for the Gaussian process regression model. The combination of these parameters forms a multidimensional feature space that reflects the varying characteristics of various aspects of the battery during the charging process. By inputting these features into the Gaussian process regression model, a health status prediction model based on battery charging data is established. Gaussian process regression is a nonparametric regression method that effectively handles uncertainty in battery health status prediction and provides high-accuracy prediction results when dealing with complex nonlinear relationships. In the Gaussian process regression model, the kernel function parameters are optimized using maximum likelihood estimation. The kernel function is a key component of Gaussian process regression and determines the measure of similarity between data. By optimizing the kernel function parameters using maximum likelihood estimation, the model better fits the voltage and current data during battery charging, improving the model's ability to predict battery health status. The optimal kernel function parameter set obtained after optimization is used to calculate the prediction mean and prediction variance of the Gaussian process regression model. The predicted mean represents the model's estimate of the battery's state of health, while the predicted variance provides information on the uncertainty of this estimate, reflecting the model's confidence level given the input data. Error analysis is performed on the prediction results. This error analysis helps understand the model's prediction accuracy and provides a basis for correction. Based on this, Bayesian theory is applied to probabilistically correct the prediction results. By combining prior knowledge with observed data, Bayesian theory effectively corrects the prediction results to obtain a state of health estimate. The corrected state of health value is then compared with a preset state of health threshold. This threshold is determined based on the battery's design standards, operating conditions, and historical data to determine whether the battery's current state of health meets normal operating requirements.If the corrected health status value is lower than the preset threshold, it means that the battery has performance degradation, insufficient capacity, or other faults. Conversely, if the health status value is higher than the threshold, it means that the battery is in good working condition. In this way, the battery health status is monitored in real time and the battery health status value is obtained.

[0038] S6, updating the polynomial mapping coefficients of the battery health factor model and the weight parameters of the battery charging curve reconstruction model according to the battery state of charge value and the battery health state value, to obtain a target health factor model and a target charging curve reconstruction model.

[0039] Specifically, residuals are calculated for the capacity decay and coulombic efficiency mapping function coefficients in the battery health factor model based on the battery state of charge and state of health values. The difference between the model's predicted capacity decay and coulombic efficiency and the actual measured results is quantified to produce a residual vector, which reflects the deviation between the model output and the actual measured values. Based on the residual vector, the coefficients of the capacity decay and coulombic efficiency mapping functions are recursively updated. This update process utilizes a residual feedback mechanism to adjust the mapping function coefficients, enabling the model to more accurately reflect the actual battery health in the next iteration. This recursive update calculation gradually adjusts the capacity decay and coulombic efficiency coefficients based on the magnitude and direction of the residual vector, thereby optimizing the predictive capability of the health factor model and ensuring its adaptability to the dynamic changes of the battery under different operating conditions. Furthermore, a sensitivity analysis is performed on the extreme learning machine (ELM) in the battery charging curve reconstruction model to optimize the input weights and bias parameters. The ELM is an efficient feedforward neural network whose training relies on the optimization of input weights and bias parameters. Sensitivity analysis evaluates the impact of each parameter on the model output, resulting in a parameter sensitivity matrix reflecting the sensitivity of the model output to different parameters. Based on the sensitivity matrix, the input weights and bias parameters are optimized and adjusted to enable the extreme learning machine to better adapt to the characteristic changes during battery charging, improve the prediction accuracy of the charging curve reconstruction model, and obtain updated network parameters. Based on the updated set of mapping coefficients, the battery health factor model is reconstructed. By substituting the coefficients of the updated capacity decay and Coulomb efficiency mapping functions into the original health factor model, the battery health factor is recalculated to obtain the target health factor model. Through continuous iterative updates, the health factor model increasingly accurately reflects the actual health status of the battery. Similarly, based on the updated network parameters, the parameters of the battery charging curve reconstruction model are updated to obtain the target charging curve reconstruction model.

[0040] In one example, the impedance characteristics of a sweeper's power battery are collected under various operating conditions. The battery operating condition characteristic data is obtained by measuring a random low-frequency modulated multi-sine excitation signal, including:

[0041] The voltage and current data of the sweeper's power battery are sampled when it is running under low-speed sweeping conditions, medium-speed sweeping conditions, high-speed sweeping conditions, no-load driving conditions, loaded driving conditions, and comprehensive operating conditions to obtain the original operating data;

[0042] Perform statistical calculations on the start-stop frequency in the original operating data, and analyze the load variation characteristics to obtain the operating characteristic parameters;

[0043] According to the characteristic parameters of the working condition, the excitation amplitude of the random low-frequency modulated multi-sine excitation signal is set, and the excitation frequency range is set to 0.01Hz to 1000Hz to obtain the target excitation signal;

[0044] Applying a target excitation signal to the power battery, collecting the voltage response and current response of the power battery under various operating conditions to obtain impedance measurement data, and based on the impedance measurement data, separating and calculating the ohmic internal resistance component, the electrochemical polarization internal resistance component, and the concentration polarization internal resistance component to obtain impedance characteristic parameters;

[0045] According to the impedance characteristic parameters, the internal resistance change trend of the power battery under various operating conditions is analyzed to obtain the impedance change characteristic data. The original operating condition data, operating condition characteristic parameters, impedance measurement data and impedance change characteristic data are fused to obtain the battery operating condition characteristic data.

[0046] In this example, data is sampled from the power battery of a sweeper under different operating conditions, including low-speed sweeping conditions, medium-speed sweeping conditions, high-speed sweeping conditions, no-load driving conditions, loaded driving conditions, and comprehensive operating conditions. Under these different operating conditions, the changes in battery voltage and current reflect the working status and performance of the battery. Collecting and analyzing this data provides a basis for subsequent battery status estimation. Under each operating condition, the battery voltage is obtained through sampling. and current Data. These data are recorded in real time by the battery management system (BMS) or other collection equipment. The collected raw operating data include the changes in the voltage and current of the battery under different operating conditions over time, expressed as and ,in Indicates time. In order to analyze the performance of the battery under different working conditions, these data are analyzed. Statistical calculation of the start-stop frequency. The start-stop frequency refers to the number of charge and discharge cycles of the battery under working conditions. In the battery management system, this frequency is counted by detecting changes in the battery charge and discharge process. For example, under low-speed cleaning conditions, the battery starts and stops frequently, resulting in a high start-stop frequency, while under high-speed cleaning conditions, the battery start-stop frequency is relatively low. By counting the start-stop frequency ( ), obtain the frequency of battery load changes under different working conditions. This feature can reflect the load characteristics of the battery under working conditions, and thus affect the assessment of battery health. Analyze the load change characteristics. The load change characteristics refer to the load changes experienced by the battery during the working condition. By calculating the battery current ( ) reflects the change of load, and the load change rate ( ) is expressed by the following formula:

[0047] ;

[0048] in, and Respectively represent the current value when the load starts and ends, and are the time points when the load starts and ends. Through this analysis, the load changes under the working conditions are obtained. According to the characteristic parameters of the working condition, the excitation amplitude of the random low-frequency modulated multi-sine excitation signal is set, and the excitation frequency range is set to 0.01Hz to 1000Hz to generate the target excitation signal. This signal can simulate the electrochemical reaction characteristics of the battery under different loads and working conditions, and measure the impedance response of the battery through multi-frequency excitation signals. The selection of the excitation signal is very critical. Excitation signals of different frequencies will cause different electrochemical reactions inside the battery, thereby reflecting the different impedance characteristics of the battery. Target excitation signal Expressed as:

[0049] ;

[0050] in, Indicates the The amplitude of the excitation signal, It is frequencies, is the phase of the signal, is the total number of excitation signals. By setting excitation signals of different frequency ranges, the impedance characteristics of the battery are measured. After the target excitation signal is applied to the battery, the voltage response and current response data of the battery under various working conditions are collected. Through these data, the impedance measurement data of the battery is obtained. The impedance of the battery ( ) is calculated by the ratio of voltage to current:

[0051] ;

[0052] in, and The voltage response and current response of the battery at each frequency are respectively. Based on these impedance measurement data, the impedance of the battery is divided into multiple components, including ohmic internal resistance ( ), electrochemical polarization internal resistance ( ) and concentration polarization internal resistance ( These components represent the impedance characteristics of different electrochemical reactions in the battery. The ohmic internal resistance is related to the battery's conductivity, the electrochemical polarization internal resistance is related to the battery's charge and discharge reaction rate, and the concentration polarization internal resistance is related to the battery's chemical concentration gradient. To separate and calculate these internal resistance components, impedance spectroscopy is used. The battery impedance model is described by an electrochemical equivalent circuit model. A common equivalent circuit model is as follows:

[0053] ;

[0054] in, is the imaginary unit, and are the time constants of electrochemical polarization and concentration polarization, respectively. By fitting the impedance data, these internal resistance components are separated. By analyzing the impedance characteristic parameters, the internal resistance variation trend of the battery under different working conditions is obtained, which reflects the health status of the battery, because the increase in internal resistance indicates the performance degradation of the battery. Internal resistance variation characteristic data ( ) Battery aging is assessed through time series analysis and statistical methods. As battery life increases, internal resistance gradually increases, leading to a decrease in battery capacity and coulombic efficiency. Raw operating data, operating characteristic parameters, impedance measurement data, and impedance change characteristic data are fused to generate battery operating characteristic data. This data is weighted using machine learning algorithms, principal component analysis, or other data fusion methods to generate comprehensive battery operating characteristic data.

[0055] In one example, based on the battery operating condition characteristic data, an equivalent circuit model is fitted and a polynomial mapping relationship between the health factor and the capacity and coulombic efficiency is established to obtain a battery health factor model, including:

[0056] Based on the battery operating condition characteristic data, Laplace transform is performed on the voltage response and current response of the battery equivalent circuit model to obtain the s-domain transfer function parameter set;

[0057] Based on the s-domain transfer function parameter set, the battery internal resistance parameter matrix is obtained by fitting the ohmic internal resistance parameters, electrochemical polarization RC network parameters, and concentration polarization RC network parameters of the equivalent circuit model through nonlinear least squares fitting.

[0058] Perform least square fitting on the relationship between each parameter in the battery internal resistance parameter matrix and the number of battery cycles to obtain a set of internal resistance attenuation characteristic curves;

[0059] Based on the set of internal resistance attenuation characteristic curves, a capacity attenuation polynomial model is constructed, and a set of capacity attenuation coefficients is calculated. At the same time, a capacity attenuation mapping function is established;

[0060] Based on the set of internal resistance attenuation characteristic curves, a Coulomb efficiency attenuation polynomial model is constructed, and the set of Coulomb efficiency coefficients is calculated. At the same time, a Coulomb efficiency mapping function is established.

[0061] The capacity decay mapping function and the Coulomb efficiency mapping function are weightedly combined to construct an initial model of the battery health factor;

[0062] A five-fold cross-validation was performed on the weight coefficients of the initial battery health factor model, with the validation error threshold ε = 0.01. The optimal weight coefficient set was obtained by iterative optimization by minimizing the root mean square error (RMSE).

[0063] According to the optimal weight coefficient set, the parameters of the initial battery health factor model are updated to construct a battery health factor model.

[0064] In this example, based on the battery operating condition characteristic data, the voltage response and current response of the battery equivalent circuit model are Laplace transformed to obtain the s-domain transfer function parameter set. The equivalent circuit model of the battery consists of the ohmic internal resistance ( )、Electrochemical polarization internal resistance( ) and concentration polarization internal resistance ( ) structure. To obtain the battery's response characteristics at different frequencies, the Laplace transform is used to convert the voltage and current responses from the time domain to the s domain (complex frequency domain). The battery's voltage and current signals in the time domain are converted to transfer functions in the Laplace domain. For the battery equivalent circuit model, the transfer function is expressed as:

[0065] ;

[0066] in, and are the Laplace transform results of the battery voltage and current, is a complex frequency domain variable, and is the time constant of electrochemical polarization and concentration polarization. Through these transfer functions, the frequency domain response characteristics of the battery are obtained. Based on the s-domain transfer function parameter set, the internal resistance parameters of the battery are estimated by the nonlinear least squares fitting method, including ohmic internal resistance, polarization internal resistance and concentration polarization internal resistance. The goal of nonlinear least squares fitting is to minimize the error between the model output (i.e., the predicted value of the voltage and current response of the battery) and the experimental data. The voltage and current responses obtained by the experiment are set to and , then the least squares fitting objective is expressed as:

[0067] ;

[0068] in, is the number of data points, For the By minimizing the above error, we can obtain the parameter set of the battery equivalent circuit model, namely the ohmic internal resistance parameter , electrochemical polarization internal resistance parameters , concentration polarization internal resistance parameters and their time constants and These parameters constitute the internal resistance parameter matrix of the battery, which is expressed as:

[0069] ;

[0070] According to the relationship between the parameters in the internal resistance parameter matrix and the number of battery cycles, the internal resistance attenuation characteristic curve is fitted by the least square fitting method. Assuming that the number of battery cycles is , the internal resistance parameters will change after each charge and discharge process, and the internal resistance decay is expressed as a function related to the number of cycles. By fitting the relationship between the internal resistance parameters and the number of battery cycles, the internal resistance decay characteristic curve is obtained. For example, the relationship of capacity decay is approximately:

[0071] ;

[0072] in, is the initial ohmic internal resistance, is the attenuation coefficient, is the number of cycles. Similarly, attenuation models are established for the electrochemical polarization internal resistance and the concentration polarization internal resistance. Based on the set of internal resistance attenuation characteristic curves, polynomial models for capacity attenuation and Coulombic efficiency attenuation are constructed. Assume that the polynomial model for capacity attenuation is:

[0073] ;

[0074] in, Indicates the The capacity of the battery at the time of the cycle, are the polynomial coefficients to be determined. These coefficients are calculated through least squares fitting, and the capacity decay mapping function is established. Similarly, the coulombic efficiency decay model is expressed as:

[0075] ;

[0076] in, For the The coulombic efficiency of the battery at the time of the first cycle, is the polynomial coefficient to be determined. Through similar steps, the mapping function of Coulomb efficiency decay is established. The capacity decay mapping function and the Coulomb efficiency mapping function are weightedly combined to obtain the initial model of the battery health factor. The battery health factor is calculated by the weighted combination of capacity decay and Coulomb efficiency, and the formula is:

[0077] ;

[0078] in, and is a weighted coefficient that represents the contribution of capacity decay and coulombic efficiency to the battery health factor. The weight coefficient of the initial battery health factor model is optimized through five-fold cross validation to evaluate the generalization ability of the model and avoid overfitting problems. The validation error threshold is set to , iterative optimization is performed by minimizing the root mean square error, and the formula is as follows:

[0079] ;

[0080] in, is the health factor predicted by the model, is the actual measured health factor, is the number of data points in the validation set. By optimizing the RMSE, the optimal set of weight coefficients is obtained. Based on this optimal set of weight coefficients, the parameters of the initial battery health factor model are updated, ultimately constructing an accurate battery health factor model.

[0081] In one example, based on the charging data in the battery operating condition characteristic data, a charging process feature extraction and analysis is performed to obtain a battery charging curve reconstruction model, including:

[0082] The charging data in the battery operating condition characteristic data is segmented and divided into the charging start segment, constant current charging segment, constant voltage charging segment, and charging termination segment according to the voltage rise rate and current change rate to obtain a segmented charging characteristic data matrix;

[0083] Based on the segmented charging characteristic data matrix, the voltage characteristic points and current characteristic points of each segment of charging data are extracted by genetic algorithm to obtain a set of characteristic points;

[0084] Construct feature vectors for the feature point set, combine the voltage feature vectors and the current feature vectors into a training sample set, and obtain the extreme learning machine input data matrix;

[0085] According to the extreme learning machine input data matrix, an extreme learning machine network structure with L hidden layer nodes is constructed, and the input weights and bias parameters are optimized by the hill climbing algorithm to obtain the initial network parameter set;

[0086] Based on the initial network parameter set, the output weights of the extreme learning machine are analytically solved to obtain a charging curve mapping model. The error between the prediction results of the charging curve mapping model and the actual charging curve is calculated to obtain the model evaluation index.

[0087] The model evaluation indicators are iteratively optimized to obtain the optimal network parameter set. Based on the optimal network parameter set, the parameters of the charging curve mapping model are updated to obtain the battery charging curve reconstruction model.

[0088] In this example, the charging data from the battery operating condition characteristic data is segmented. The charging data includes the changes in the battery's voltage and current over time during the charging process. The charging process is divided into the charging start phase, constant current charging phase, constant voltage charging phase, and charging termination phase. The judgment is made based on the voltage rise rate and current change rate. The voltage rise rate and current change rate are key characteristics of the charging process and are calculated using the following formula:

[0089] ;

[0090] ;

[0091] in, and Time points The battery voltage and current at is the time interval. Based on these rates of change, the charging stages are divided. For example, when the voltage rise rate is high, it indicates the charging start stage or constant current stage; when the voltage approaches a constant value and the current changes little, it enters the constant voltage stage; and when the current drops sharply, it indicates the charging end stage. This segmentation results in a charging characteristic data matrix, where each row represents data for a charging stage, including information such as voltage and current. Based on the segmented charging characteristic data matrix, a genetic algorithm is used to extract the voltage and current characteristic points for each charging stage. A genetic algorithm is a heuristic search algorithm that mimics the process of natural selection, gradually optimizing parameters through selection, crossover, and mutation. The genetic algorithm automatically selects key characteristic points in the voltage and current curves to represent the characteristic information of each charging stage. The goal of feature point extraction is to identify key moments in the voltage and current changes during the charging process, such as when the voltage changes from a rapid rise to a stable state or when the current drops from a high value to a low value. By setting an appropriate objective function, such as maximizing the discrimination of feature points or minimizing the error, the genetic algorithm is used to extract the most representative feature point set. Feature vectors are then constructed based on the extracted voltage and current feature point sets. The voltage feature points and current feature points of each charging stage are combined into a feature vector and form a complete training sample set. Assume that the voltage feature point is , the current characteristic point is , then the characteristic vector of each charging stage is expressed as:

[0092] ;

[0093] These eigenvectors constitute the input data matrix of the extreme learning machine model. Assume that the input data matrix is , each column corresponds to a set of feature points, and each row is a training sample. Use this data to build an extreme learning machine model. The extreme learning machine is a feedforward neural network with a single hidden layer, and the number of nodes in the hidden layer is specified by the user. Set the extreme learning machine network structure, assuming that the number of hidden layer nodes is , then the weight matrix between the input data and the hidden layer and the bias matrix Need to be optimized. The output of the extreme learning machine is:

[0094] ;

[0095] in, is the activation function (usually sigmoid or ReLU), is the input matrix, is the weight from the input layer to the hidden layer, is the bias. By calculating the output of the hidden layer , and get the final output weight matrix , the matrix and the output data The relationship between them is:

[0096] ;

[0097] The input weights and bias parameters are optimized using a hill climbing algorithm. Hill climbing is a greedy optimization algorithm that searches for better solutions through local search. Based on the initial weights and biases, the hill climbing algorithm adjusts them to minimize the error between the predicted results and the actual charging data. The optimization goal is to minimize the model's error, such as the mean squared error (MSE):

[0098] ;

[0099] in, is the charging curve output predicted by the model, is the actual charging curve data, is the number of samples. By minimizing the MSE, we get the initial network parameter set, that is, the optimized input weights and biases. Based on the initial network parameter set, we solve the output weights of the ELM analytically to get the weight matrix of the output layer. After obtaining the complete ELM network model, the mapping function of the battery charging curve is obtained. The error between the predicted result of the charging curve and the actual charging curve is calculated to obtain the model evaluation index, which includes the root mean square error (RMSE) and the determination coefficient ( )wait:

[0100] ;

[0101] ;

[0102] in, is the mean of the actual charging data. The model's accuracy is determined by analyzing the model's evaluation metrics, and iterative optimization is performed as needed. Based on the optimal set of network parameters, the parameters of the charging curve mapping model are updated to obtain the final reconstructed model of the battery charging curve. This model can predict changes in the charging process based on the battery's charging data.

[0103] In one example, an extended Kalman filter operation is performed on the polynomial mapping relationship in the battery health factor model to obtain a battery state of charge value, including:

[0104] Perform parameter calculation on the capacity decay mapping function in the battery health factor model to obtain the actual capacity value, and perform parameter calculation based on the coulomb efficiency mapping function in the battery health factor model to obtain the coulomb efficiency value;

[0105] Based on the actual capacity and coulomb efficiency values, the battery state space equation is constructed to obtain a state equation model. The nonlinear relationship between the battery terminal voltage and the state of charge is modeled, and the observation equation is constructed to obtain an observation equation model.

[0106] Based on the state equation model and the observation equation model, the state prediction value and the error covariance matrix are calculated to obtain the prior state quantity. Based on the prior state quantity and the observation equation, the Kalman gain matrix is calculated to obtain the filter gain coefficient.

[0107] Based on the filter gain coefficient, the state prediction value is corrected and calculated to obtain the posterior state quantity, and the battery state of charge value is obtained by updating the error covariance matrix according to the posterior state quantity.

[0108] In this example, the capacity decay mapping function and coulombic efficiency mapping function in the battery health factor model are the basis of battery health management and can reflect the difference between the actual performance of the battery and the ideal state. The capacity decay mapping function is obtained by fitting historical data and represents the capacity decay of the battery under different usage conditions. Assume that the capacity decay mapping function is:

[0109] ;

[0110] in, Indicates the battery time The capacity of is the initial capacity, Is the capacity attenuation rate. By performing regression analysis on the battery usage data, the attenuation rate is obtained. According to the decay rate , calculate the actual capacity of the battery at any time. The Coulomb efficiency mapping function related to capacity decay is used to describe the efficiency change of the battery during the charging and discharging process. Assume that the Coulomb efficiency mapping function is:

[0111] ;

[0112] in, For battery in time The Coulombic efficiency when is the initial Coulombic efficiency, is the Coulomb efficiency decay rate. Similar to capacity decay, the parameter is obtained through experimental data. and , and thus calculate the coulombic efficiency. According to the actual capacity value and Coulombic efficiency values , construct the state space equation of the battery. The state space equation is a mathematical model that describes the dynamic changes of the system and is used to predict the system state. In battery management, the system state includes the battery state of charge (SOC), battery voltage ( ) and current ( ) etc. The battery's SOC is a key parameter that describes the remaining battery capacity. There is a complex nonlinear relationship between the battery's SOC and the battery's voltage and current. This relationship is modeled using state equations and observation equations. The battery state space equation is expressed as:

[0113] ;

[0114] in, is a state vector, including the battery's state of charge (SOC) and other possible state quantities, such as battery voltage ( )、Current( ); is the control input (e.g., charge and discharge current); and The state transfer matrix and control matrix describe the dynamic behavior of the system respectively; is the process noise, which is assumed to be zero-mean Gaussian noise. The nonlinear relationship between battery voltage and SOC is modeled by the observation equation. The observation equation is expressed as:

[0115] ;

[0116] in, is the observed quantity, usually the battery terminal voltage; It is a nonlinear function that represents the relationship between battery voltage and SOC; is the observation noise, which is assumed to be zero-mean Gaussian noise. Based on the state space model and observation equation, the Kalman filter can estimate the battery SOC through two steps: prediction and update. The Kalman filter calculates the state prediction value and the error covariance matrix to obtain the prior state quantity. Assume that the prior state quantity is , and its calculation formula is:

[0117] ;

[0118] in, is the estimated value at the previous moment, Is the next moment state of the prediction. The error covariance matrix represents the uncertainty of the prediction value, which is expressed as:

[0119] ;

[0120] in, is the error covariance matrix at the previous moment, is the process noise covariance matrix, which represents the uncertainty of the system. The Kalman gain matrix is calculated by combining the observation equation to optimally combine the prior state and the observation value. The Kalman gain matrix is calculated as:

[0121] ;

[0122] in, is the observation matrix, which represents the relationship between states and observations, is the observation noise covariance matrix, which represents the uncertainty of the observation. Kalman gain It is used to perform a weighted average of the predicted state and the actual observation to obtain the optimal state estimate. Based on the Kalman gain, the state prediction value is corrected and calculated to obtain the posterior state quantity. The update formula of the posterior state quantity is:

[0123] ;

[0124] in, is the actual observed battery voltage, The predicted battery voltage is obtained based on the predicted state. Through this update step, the Kalman filter algorithm effectively corrects the state estimate and obtains the accuracy of the state estimate at subsequent moments through the updated error covariance matrix. Based on the posterior state, the error covariance matrix is updated to obtain the battery state of charge value.

[0125] In one example, based on a battery charging curve reconstruction model, the voltage and current data during the charging process are segmented and Gaussian process regression is performed to obtain the battery health status value, including:

[0126] Based on the charging data output by the battery charging curve reconstruction model, the voltage curve and current curve are segmented according to the charging stage to obtain the charging stage segmented data;

[0127] Integrate the voltage and current data of the segmented data of the charging stage, and calculate the charging time of each stage to obtain the charging capacity parameters and charging time parameters;

[0128] According to the voltage sequence in the segmented data of the charging stage, the voltage difference between adjacent sampling points is calculated and divided by the sampling time interval to obtain the voltage change rate parameter;

[0129] The charging capacity parameter, charging time parameter and voltage change rate parameter are combined to construct a training sample matrix and obtain Gaussian process regression input data;

[0130] The Gaussian process regression input data is input into the Gaussian process regression model. The kernel function parameters are optimized using the maximum likelihood estimation method to obtain the optimal kernel function parameter set. Based on the optimal kernel function parameter set, the predicted mean and predicted variance of the Gaussian process regression model are calculated to obtain the battery health status prediction result.

[0131] The prediction results are analyzed for errors, and the prediction results are probability-corrected using Bayesian theory to obtain a corrected health status value. The corrected health status value is then compared and analyzed with the preset health status threshold to obtain the battery health status value.

[0132] In this example, the battery charging process is divided into several different stages, such as the charging start stage, constant current charging stage, constant voltage charging stage and charging termination stage. According to the voltage and current curves in the charging data, these curves are segmented to obtain segmented data of different charging stages. The voltage rise rate and current change rate are used as criteria for determining the division of each stage. For example, if the voltage rise rate exceeds a certain set threshold, it is determined to be a constant current stage; when the voltage reaches the set constant voltage value, it enters the constant voltage charging stage. According to these judgment rules, the battery charging curve is divided into multiple charging stages. The voltage and current data of each stage are integrated. The charging time and charging capacity of each charging stage are calculated. The charging capacity is estimated by integrating the current over time. Assuming that in the first The charging current in this stage is , charging time is , then the charging capacity of this stage Expressed as:

[0133] ;

[0134] in, and are the start and end time of the stage respectively. By integrating the current, the charging capacity of each stage is obtained, and thus the total capacity of the charging process is calculated. By calculating the difference between the voltages of adjacent sampling points and dividing it by the sampling time interval, the voltage change rate of each charging stage is calculated. If the voltage sequence is , then the voltage change rate Expressed as:

[0135] ;

[0136] in, and The battery at the time and The voltage value, The sampling interval is denoted by . The battery's charging characteristics at different stages are evaluated by calculating the voltage change rate. The charging capacity, charging time, and voltage change rate parameters are combined to construct a training sample matrix. These parameters collectively describe the battery's performance during charging and serve as input data for the Gaussian process regression model. Assume that the charging capacity, charging time, and voltage change rate form a feature vector:

[0137] ;

[0138] in, Indicates the The characteristic vectors of the charging stage. By combining the characteristic vectors of all stages into a training sample set, the input data matrix of Gaussian process regression is obtained. The Gaussian process regression model is a non-parametric regression method that can make predictions based on training data without explicitly assuming the form of the function. In Gaussian process regression, it is assumed that the output variable (battery health status) is generated by the input variable (charging process characteristics) through a Gaussian process and has a Gaussian distribution. The kernel function parameters are optimized by the maximum likelihood estimation method to find the optimal kernel function parameter set. Assume that the kernel function of Gaussian process regression is:

[0139] ;

[0140] in, is the signal amplitude, is the length scale, and are the two eigenvectors in the input data matrix. The parameters of the kernel function are optimized by the maximum likelihood estimation method. and , and obtain the optimal kernel function, thereby improving the prediction accuracy of the regression model. After obtaining the optimal kernel function parameters, the Gaussian process regression model is used for prediction, and the mean and variance of the prediction are calculated. The mean of the prediction result represents the estimated value of the battery health state, while the variance represents the uncertainty of the prediction. and variance Calculated by the following formula:

[0141] ;

[0142] ;

[0143] in, is the output data of the training sample (battery health status), is the covariance matrix of the training samples, is the noise variance, is the covariance between the new sample and the training sample. Through these formulas, the predicted results of the battery health state and the corresponding uncertainty are obtained. The prediction results are analyzed for errors and the probability of the prediction results is corrected using Bayesian theory. The Bayesian method updates the prediction results based on prior knowledge and observed data to obtain the corrected health state value. Assuming the prior distribution is , the prediction result is , then the posterior distribution is:

[0144] ;

[0145] in, is the likelihood function, which represents the given health state When the observation data probability; is the prior distribution. Through Bayesian updating, a revised health status value is obtained. The battery's health status is determined by comparing the revised health status value with a preset health status threshold. If the revised health status value falls below a preset threshold, it indicates a battery problem and requires maintenance or replacement.

[0146] In one example, based on the battery state of charge value and the battery state of health value, the polynomial mapping coefficients of the battery health factor model and the weight parameters of the battery charging curve reconstruction model are updated to obtain the target health factor model and the target charging curve reconstruction model, including:

[0147] According to the battery state of charge value and the battery health state value, the capacity attenuation mapping function coefficient and the coulomb efficiency mapping function coefficient of the battery health factor model are calculated as residuals to obtain a residual vector;

[0148] Based on the residual vector, the coefficients of the capacity attenuation mapping function and the Coulomb efficiency mapping function are recursively updated to obtain an updated mapping coefficient set;

[0149] Perform sensitivity analysis on the input weights and bias parameters of the extreme learning machine in the battery charging curve reconstruction model to obtain a parameter sensitivity matrix. Based on the parameter sensitivity matrix, optimize and adjust the input weights and bias parameters to obtain updated network parameters.

[0150] According to the updated mapping coefficient set, the battery health factor model is reconstructed to obtain the target health factor model, and based on the updated network parameters, the battery charging curve reconstruction model is parameter updated to obtain the target charging curve reconstruction model.

[0151] In this example, given the battery's state of charge and health status, the residual vector is calculated based on the capacity decay mapping function and coulombic efficiency mapping function in the battery health factor model. The capacity decay mapping function and coulombic efficiency mapping function represent the variation of the battery's capacity decay and coulombic efficiency, respectively, and are represented by polynomials or other mathematical functions. Assume that the capacity decay mapping function is:

[0152] ;

[0153] in, Indicates the relationship between battery capacity and state of charge, is the coefficient of the mapping function, and SOC is the state of charge value. Similarly, the Coulomb efficiency mapping function is expressed as:

[0154] ;

[0155] in, It represents the relationship between battery coulombic efficiency and state of charge, are the coefficients of the mapping function, and SOC is the state of charge value. To optimize these mapping functions, a residual vector is calculated, which represents the difference between the actual measured battery health state value and the health state value calculated based on the model. The residual vector Expressed as:

[0156] ;

[0157] in, is the actual measured battery health status value, The battery health status value is calculated based on the model. By calculating the residual vector, the model error is evaluated and the basis for subsequent parameter updates is provided. Based on the residual vector, the coefficients of the capacity decay mapping function and the coulomb efficiency mapping function are recursively updated. The coefficients are updated using gradient descent or other optimization algorithms. Assume that in the In the iterations, the coefficients of the mapping function are and , the coefficients are updated using the following formula:

[0158] ;

[0159] ;

[0160] in, is the learning rate, and They are the gradients of the loss function with respect to the coefficients of the capacity attenuation mapping function and the coefficients of the Coulomb efficiency mapping function. Expressed as:

[0161] ;

[0162] in, is the sample size, It is The residual of each sample is calculated by recursively updating these coefficients, so that the model gradually reduces the error in each iteration and improves the accuracy of the battery health factor model. At the same time, a sensitivity analysis is performed on the input weights and bias parameters of the extreme learning machine in the battery charging curve reconstruction model. The extreme learning machine is a machine learning model based on a single hidden layer neural network, which has the advantages of fast training and high accuracy. In the extreme learning machine, the input weights and bias parameters directly affect the performance of the model, and a sensitivity analysis is performed. Assume that the network structure of the extreme learning machine is:

[0163] ;

[0164] in, is the output of the model, is the output weight, is the activation function, is the output of the hidden layer node, For input data, is the bias parameter. By calculating the impact of each input weight and bias parameter on the model output, the parameter sensitivity matrix is obtained, which represents the sensitivity of each parameter to the model prediction result. The calculation is achieved through the following formula:

[0165] ;

[0166] in, Indicates the The input weights The impact of the model output. Through sensitivity analysis, the parameters that have the greatest impact on the model output are identified, and these parameters can be optimized in a targeted manner. Based on the parameter sensitivity matrix, the input weights and bias parameters are optimized and adjusted. The optimization goal is to minimize the error between the model's predicted results and the actual results. The weights and bias parameters are updated using the gradient descent method as shown below:

[0167] ;

[0168] ;

[0169] in, and are the gradients of the loss function with respect to the weights and biases, respectively. The battery health factor model is reconstructed based on the updated input weights and bias parameters to obtain the target health factor model. Simultaneously, the battery charging curve reconstruction model is updated based on the updated network parameters to obtain the target charging curve reconstruction model. Through iterative optimization, the battery health factor model and charging curve reconstruction model are continuously improved to provide accurate battery state estimation under different operating conditions.

[0170] Reference Figure 2 This embodiment provides a device for estimating the state of a power battery of a sweeping vehicle, comprising:

[0171] Acquisition module 1 is used to collect impedance characteristics of the power battery of the sweeper under various working conditions, and obtain battery working condition characteristic data by measuring the random low-frequency modulated multi-sinusoidal excitation signal;

[0172] Establishing module 2, which is used to perform fitting calculations through an equivalent circuit model based on the battery operating condition characteristic data, and establish a polynomial mapping relationship between the health factor and the capacity and coulomb efficiency to obtain a battery health factor model;

[0173] Analysis module 3, used to extract and analyze charging process characteristics based on the charging data in the battery operating condition characteristic data to obtain a battery charging curve reconstruction model;

[0174] Operation module 4 is used to perform an extended Kalman filter operation on the polynomial mapping relationship in the battery health factor model to obtain a battery state of charge value;

[0175] Processing module 5 is used to rebuild the model based on the battery charging curve, perform segmented processing and Gaussian process regression calculation on the voltage and current data during the charging process, and obtain the battery health status value;

[0176] The updating module 6 is used to update the polynomial mapping coefficients of the battery health factor model and the weight parameters of the battery charging curve reconstruction model according to the battery state of charge value and the battery health state value to obtain a target health factor model and a target charging curve reconstruction model.

[0177] In this embodiment, for the specific implementation of each unit in the above device embodiment, please refer to the above method embodiment, which will not be repeated here.

[0178] Reference Figure 3 In an embodiment of the present invention, a computer device is also provided. The computer device may be a server, and its internal structure may be as follows: Figure 3 As shown. The computer device includes a processor, memory, display screen, input device, network interface and database connected via a system bus. The processor of the computer design is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store the corresponding data in this embodiment. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, the above method is implemented.

[0179] Those skilled in the art will understand that Figure 3 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present invention and does not constitute a limitation on the computer device to which the solution of the present invention is applied.

[0180] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which implements the above-described method when executed by a processor. It is understood that the computer-readable storage medium in this embodiment can be a volatile readable storage medium or a non-volatile readable storage medium.

[0181] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing the relevant hardware using a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the above-described method embodiments. Any reference to memory, storage, database, or other media provided herein and used in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double-speed SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct RAMbus dynamic RAM (DRDRAM), and RAMbus dynamic RAM.

[0182] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, apparatus, article, or method comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, apparatus, article, or method. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, apparatus, article, or method comprising the element.

[0183] The above description is only a preferred embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for estimating the state of a power battery of a sweeping vehicle, characterized in that: The following steps are involved: The impedance characteristics of the sweeper's power battery are collected under various operating conditions, and the battery operating condition characteristic data is obtained by measuring the random low-frequency modulated multi-sine excitation signal. According to the battery operating condition characteristic data, a fitting operation is performed through an equivalent circuit model, and a polynomial mapping relationship between the health factor and the capacity and coulombic efficiency is established to obtain a battery health factor model; Based on the charging data in the battery operating condition characteristic data, a charging process feature extraction and analysis is performed to obtain a battery charging curve reconstruction model; specifically, the method includes: performing segmented processing on the charging data in the battery operating condition characteristic data, dividing the charging data in the battery operating condition characteristic data into a charging start segment, a constant current charging segment, a constant voltage charging segment, and a charging termination segment according to the voltage rise rate and the current change rate, and obtaining a segmented charging characteristic data matrix; Based on the segmented charging characteristic data matrix, feature extraction is performed on the voltage feature points and current feature points of each segment of charging data using a genetic algorithm to obtain a feature point set; feature vectors are constructed on the feature point set, and the voltage feature vectors and current feature vectors are combined into a training sample set to obtain an extreme learning machine input data matrix; based on the extreme learning machine input data matrix, an extreme learning machine network structure with L hidden layer nodes is constructed, and input weights and bias parameters are optimized using a hill climbing algorithm to obtain an initial network parameter set; based on the initial network parameter set, the output weights of the extreme learning machine are analytically solved to obtain a charging curve mapping model, and an error calculation is performed between the predicted result of the charging curve mapping model and the actual charging curve to obtain a model evaluation index; the model evaluation index is iteratively optimized to obtain an optimal network parameter set, and the parameters of the charging curve mapping model are updated based on the optimal network parameter set to obtain a battery charging curve reconstruction model; Performing an extended Kalman filter operation on the polynomial mapping relationship in the battery health factor model to obtain a battery state of charge value; Based on the battery charging curve reconstruction model, the voltage and current data during the charging process are processed in segments and Gaussian process regression is performed to obtain the battery health status value; According to the battery state of charge value and the battery state of health value, the polynomial mapping coefficients of the battery health factor model and the weight parameters of the battery charging curve reconstruction model are updated to obtain a target health factor model and a target charging curve reconstruction model.

2. The method for estimating the state of the power battery of a sweeping vehicle according to claim 1, characterized in that: The impedance characteristics of the power battery of the sweeper are collected under various working conditions, and the battery working condition characteristic data is obtained by measuring the random low-frequency modulated multi-sine excitation signal, including: The voltage and current data of the sweeper's power battery are sampled when it is running under low-speed sweeping conditions, medium-speed sweeping conditions, high-speed sweeping conditions, no-load driving conditions, loaded driving conditions, and comprehensive operating conditions to obtain the original operating data; Statistically calculating the start-stop frequency in the original operating data, and analyzing the load variation characteristics to obtain operating characteristic parameters; According to the working condition characteristic parameters, the excitation amplitude of the random low-frequency modulated multi-sine excitation signal is set, and the excitation frequency range is set to 0.01 Hz to 1000 Hz to obtain the target excitation signal; applying the target excitation signal to the power battery, collecting the voltage response and current response of the power battery under various operating conditions to obtain impedance measurement data, and based on the impedance measurement data, separating and calculating the ohmic internal resistance component, the electrochemical polarization internal resistance component, and the concentration polarization internal resistance component to obtain impedance characteristic parameters; According to the impedance characteristic parameters, the internal resistance change trend of the power battery under various operating conditions is analyzed to obtain impedance change characteristic data, and the original operating condition operation data, the operating condition characteristic parameters, the impedance measurement data and the impedance change characteristic data are fused to obtain battery operating condition characteristic data.

3. The method for estimating the state of the power battery of a sweeping vehicle according to claim 2, characterized in that: The battery health factor model is obtained by performing a fitting operation on the equivalent circuit model based on the battery operating condition characteristic data and establishing a polynomial mapping relationship between the health factor and the capacity and coulomb efficiency, including: performing Laplace transform on the voltage response and current response of the battery equivalent circuit model according to the battery operating condition characteristic data to obtain an s-domain transfer function parameter set; Based on the s-domain transfer function parameter set, the ohmic internal resistance parameters, electrochemical polarization RC network parameters, and concentration polarization RC network parameters of the equivalent circuit model are fitted by nonlinear least squares to obtain a battery internal resistance parameter matrix; Performing least squares fitting on the relationship between each parameter in the battery internal resistance parameter matrix and the number of battery cycles to obtain a set of internal resistance attenuation characteristic curves; According to the internal resistance attenuation characteristic curve set, a capacity attenuation polynomial model is constructed, and a capacity attenuation coefficient set is calculated and a capacity attenuation mapping function is established; Based on the internal resistance attenuation characteristic curve set, a Coulomb efficiency attenuation polynomial model is constructed, and a Coulomb efficiency coefficient set is calculated and a Coulomb efficiency mapping function is established; Performing a weighted combination of the capacity decay mapping function and the coulombic efficiency mapping function to construct an initial battery health factor model; Perform a five-fold cross validation on the weight coefficients of the initial model of the battery health factor, set the validation error threshold ε=0.01, and perform iterative optimization by minimizing the root mean square error RMSE to obtain the optimal weight coefficient set; According to the optimal weight coefficient set, the parameters of the battery health factor initial model are updated to construct a battery health factor model.

4. The method for estimating the state of the power battery of a sweeping vehicle according to claim 1, characterized in that: The performing of an extended Kalman filter operation on the polynomial mapping relationship in the battery health factor model to obtain a battery state of charge value includes: Performing parameter calculation on the capacity decay mapping function in the battery health factor model to obtain an actual capacity value, and performing parameter calculation based on the coulombic efficiency mapping function in the battery health factor model to obtain a coulombic efficiency value; Constructing a battery state space equation based on the actual capacity value and the coulombic efficiency value to obtain a state equation model, modeling a nonlinear relationship between the battery terminal voltage and the state of charge, constructing an observation equation, and obtaining an observation equation model; Based on the state equation model and the observation equation model, a state prediction value and an error covariance matrix are calculated to obtain a priori state quantity, and a Kalman gain matrix is calculated based on the priori state quantity in combination with the observation equation to obtain a filter gain coefficient; Based on the filter gain coefficient, the state prediction value is corrected and calculated to obtain a posterior state quantity, and the battery state of charge value is obtained by updating the error covariance matrix according to the posterior state quantity.

5. The method for estimating the state of the power battery of a sweeping vehicle according to claim 4, characterized in that: The battery charging curve reconstruction model is based on the battery charging curve, and the voltage and current data during the charging process are subjected to segmented processing and Gaussian process regression calculation to obtain the battery health status value, including: Based on the charging data output by the battery charging curve reconstruction model, the voltage curve and the current curve are segmented according to the charging stage to obtain charging stage segmented data; Integrating the voltage and current data of the segmented data of the charging stage, and calculating the charging time of each stage to obtain a charging capacity parameter and a charging time parameter; According to the voltage sequence in the segmented data of the charging stage, the voltage difference between adjacent sampling points is calculated and divided by the sampling time interval to obtain a voltage change rate parameter; Performing feature combination on the charging capacity parameter, the charging time parameter, and the voltage change rate parameter to construct a training sample matrix and obtain Gaussian process regression input data; Inputting the Gaussian process regression input data into a Gaussian process regression model, optimizing kernel function parameters using a maximum likelihood estimation method to obtain an optimal kernel function parameter set, and calculating a predicted mean and a predicted variance of the Gaussian process regression model based on the optimal kernel function parameter set to obtain a battery health status prediction result; The prediction result is subjected to error analysis, and the prediction result is subjected to probability correction using Bayesian theory to obtain a corrected health status value. The corrected health status value is then compared and analyzed with a preset health status threshold to obtain a battery health status value.

6. The method for estimating the state of the power battery of a sweeping vehicle according to claim 5, characterized in that: The updating of the polynomial mapping coefficients of the battery health factor model and the weight parameters of the battery charging curve reconstruction model according to the battery state of charge value and the battery health state value to obtain a target health factor model and a target charging curve reconstruction model includes: performing residual calculation on the capacity attenuation mapping function coefficient and the coulomb efficiency mapping function coefficient of the battery health factor model according to the battery state of charge value and the battery state of health value to obtain a residual vector; Based on the residual vector, recursively update the coefficients of the capacity attenuation mapping function and the coulomb efficiency mapping function to obtain an updated mapping coefficient set; Performing sensitivity analysis on input weights and bias parameters of an extreme learning machine in the battery charging curve reconstruction model to obtain a parameter sensitivity matrix, and optimizing and adjusting the input weights and bias parameters based on the parameter sensitivity matrix to obtain updated network parameters; According to the updated mapping coefficient set, the battery health factor model is reconstructed to obtain a target health factor model, and based on the updated network parameters, the battery charging curve reconstruction model is parameter updated to obtain a target charging curve reconstruction model.

7. A sweeper vehicle power battery status estimation device, characterized in that: For implementing the steps of the method according to any one of claims 1 to 6, the device comprises: The acquisition module is used to collect the impedance characteristics of the sweeper's power battery under various working conditions, and obtain the battery operating condition characteristic data by measuring the random low-frequency modulated multi-sinusoidal excitation signal; Establishing a module for performing a fitting operation through an equivalent circuit model based on the battery operating condition characteristic data, and establishing a polynomial mapping relationship between the health factor and the capacity and coulomb efficiency to obtain a battery health factor model; An analysis module, configured to extract and analyze charging process characteristics based on the charging data in the battery operating condition characteristic data to obtain a battery charging curve reconstruction model; an operation module, configured to perform an extended Kalman filter operation on the polynomial mapping relationship in the battery health factor model to obtain a battery state of charge value; a processing module, configured to reconstruct a model based on the battery charging curve, perform segmented processing and Gaussian process regression calculation on the voltage and current data during the charging process, and obtain a battery health status value; An updating module is used to update the polynomial mapping coefficients of the battery health factor model and the weight parameters of the battery charging curve reconstruction model according to the battery state of charge value and the battery health state value to obtain a target health factor model and a target charging curve reconstruction model.

8. A computer device comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images