A method and system for predicting state of health (SOH) and remaining useful life (RUL) of an energy storage battery, an electronic device, and a medium

Abstract

A SOH and RUL prediction method and system of an energy storage battery, an electronic device, and a medium relate to the technical field of energy storage battery detection. The method comprises: obtaining battery parameters of an energy storage battery and driving parameters of an electric vehicle corresponding to the energy storage battery; determining driving behavior characteristics of the electric vehicle based on the driving parameters, and determining battery aging characteristics of the energy storage battery based on the battery parameters; aligning timestamps of the driving behavior characteristics and the battery aging characteristics, and constructing a battery health characteristic vector of the energy storage battery within a preset period; inputting the battery health characteristic vector into a training model to obtain a SOH prediction model of the energy storage battery, and predicting a current battery health value of the energy storage battery based on the SOH prediction model; and predicting a current remaining battery life of the energy storage battery according to the current battery health value of the energy storage battery, a cumulative use time length, and a standard battery life. The technical solution provided in the application achieves the effect of improving the accuracy of predicting the SOH and RUL of the energy storage battery.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of energy storage battery detection, in particular to a SOH and RUL prediction method and system for an energy storage battery, an electronic device and a medium. BACKGROUND

[0002] With the transformation of global energy structure and the improvement of environmental protection requirements, electric vehicles as a clean energy transportation tool have a growing market demand. One of the core components of electric vehicles is energy storage batteries, whose performance directly affects the driving range, safety and use cost of the vehicle. Therefore, it is crucial to ensure that the battery maintains good performance during its service life. The state of health (SOH) and remaining useful life (RUL) of the battery are important indicators for evaluating the performance and safety of the battery. SOH reflects the current health status of the battery relative to a new battery, while RUL predicts the available state of the battery in the future and its possible termination time. For electric vehicle manufacturers and users, accurate prediction of the SOH and RUL of the battery not only optimizes the use of the battery and prolongs its service life, but also reduces maintenance costs and improves the reliability of the vehicle and the trust of users.

[0003] Currently, existing methods for predicting the SOH and RUL of energy storage batteries analyze the health status of the energy storage battery by detecting data of the energy storage battery to achieve the purpose of predicting the SOH and RUL of the energy storage battery. However, in actual application, due to the influence of user driving habits, the energy storage battery of the electric vehicle ages differently under different driving conditions. Predicting the battery health condition by only detecting the data of the energy storage battery often differs from the actual health condition of the energy storage battery, resulting in low accuracy in predicting the SOH and RUL of the energy storage battery. SUMMARY

[0004] The present application provides a SOH and RUL prediction method and system for an energy storage battery, an electronic device and a medium, which has the effect of improving the accuracy of predicting the SOH and RUL of the energy storage battery.

[0005] In a first aspect, the present application provides a SOH and RUL prediction method for an energy storage battery, comprising:

[0006] obtaining battery parameters of the energy storage battery and driving parameters of the electric vehicle corresponding to the energy storage battery;

[0007] determining driving behavior characteristics of the electric vehicle based on the driving parameters, and determining battery aging characteristics of the energy storage battery based on the battery parameters;

[0008] align timestamps of the driving behavior feature and the battery aging feature within a preset period, and construct a battery health feature vector of the energy storage battery within the preset period according to the driving behavior feature and the battery aging feature;

[0009] input the battery health feature vector into a training model to obtain an SOH prediction model of the energy storage battery, and predict a current battery health value of the energy storage battery based on the SOH prediction model;

[0010] predict a current remaining battery life of the energy storage battery according to the current battery health value, a cumulative use time length and a standard battery life.

[0011] By adopting the above technical solution, the battery parameters and the vehicle driving parameters are obtained, and then the driving behavior feature is determined based on the driving parameters, and the battery aging feature is determined based on the battery operation data. Then, the driving behavior feature and the battery aging feature are aligned in the time dimension, and a comprehensive feature vector describing the battery health state is constructed. The feature vector is input into a training model for training to obtain an SOH prediction model, and the current SOH of the energy storage battery, i.e. the battery health value, is predicted based on the SOH prediction model. In combination with the predicted SOH, the cumulative use time length and the standard battery life, the current RUL, i.e. the remaining battery life, is predicted. The battery parameters of the battery itself affecting the battery aging and the driving parameters of the corresponding external electric vehicle of the energy storage battery are fused, and the influence of driving habits and other use conditions on the battery degradation is considered in multiple dimensions, thereby improving the accuracy of SOH and RUL prediction.

[0012] Optionally, the current battery health value, the cumulative use time length and the standard battery life of the energy storage battery are substituted into a preset battery life prediction formula to obtain the current remaining battery life of the energy storage battery; wherein the preset battery life prediction formula is:

[0013]

[0014] In the formula, R represents the current remaining battery life of the energy storage battery, T life represents the standard life of the energy storage battery, SOH represents the current battery health value of the energy storage battery, f fast represents an aging factor of the energy storage battery in a fast charging mode, p fast represents a fast charging proportion of the energy storage battery, f slow represents an aging factor of the energy storage battery in a slow charging mode, p slow represents a slow charging proportion of the energy storage battery, T used represents the current cumulative use time length of the energy storage battery.

[0015] By adopting the above technical solutions, when predicting the remaining life of the battery, a preset battery life prediction formula is adopted, the battery health value, the cumulative use time and the standard life data are taken as model inputs, and the remaining available time of the battery is automatically output based on formula calculation. By adopting the standard formula algorithm, efficient and automatic prediction of the remaining life of a large number of batteries can be realized, and the calculation result is more accurate and reliable in combination with various influencing factors.

[0016] Optionally, according to the driving time length, the brake frequency and the driving speed in the driving parameters, a plurality of driving behaviors of the electric vehicle are determined, the driving behaviors include an emergency braking behavior, a high-speed driving behavior and a long-distance driving behavior; a driving behavior time sequence of the electric vehicle is generated according to the sampling time period of each driving behavior and the driving parameter, and the driving behavior time sequence is taken as the driving behavior feature.

[0017] By adopting the above technical solutions, according to the driving time length, the brake frequency and the driving speed and other driving parameters, a plurality of specific driving behavior types are determined, including emergency braking, high-speed driving and long-distance driving, and each aspect of the driving habit is comprehensively reflected. And based on the sampling time period, the time sequence of these driving behaviors is generated as a feature. The time sequence feature of the multiple types of driving behaviors can more comprehensively describe the use environment and the consumption process of the battery. Based on these diversified driving behavior time sequence features, a battery health evaluation model that is adaptive to various complex power consumption environments can be trained, and the prediction accuracy of the battery state can be improved.

[0018] Optionally, if the driving time length is greater than or equal to a preset time length, the long-distance driving behavior is determined as the driving behavior of the electric vehicle; if the brake frequency is greater than or equal to a preset frequency, the emergency braking behavior is determined as the driving behavior of the electric vehicle; and if the driving speed is greater than or equal to a preset speed, the high-speed driving behavior is determined as the driving behavior of the electric vehicle.

[0019] By adopting the above technical solutions, the preset thresholds of the driving time length, the brake frequency and the driving speed are set, and different types of driving behaviors are determined based on threshold judgment, including long-distance driving, emergency braking and high-speed driving. This threshold judgment-based method can clearly distinguish different driving features, simplify the complex driving process into specific behavior categories, facilitate feature extraction and modeling, and make the battery health evaluation more accurate.

[0020] Optionally, a sampling duration of the battery parameter is determined; a voltage variation rate of the energy storage battery is determined according to the sampling duration and the voltage; a resistance increase rate of the energy storage battery is determined according to the sampling duration and the internal resistance; a capacitance attenuation rate of the energy storage battery is determined according to the sampling duration and the capacitance; and the voltage variation rate, the resistance increase rate and the capacitance attenuation rate are taken as the battery aging characteristics of the energy storage battery.

[0021] By adopting the technical solution, when the battery aging characteristics are extracted, the sampling duration of the battery parameter is first determined, then the voltage variation rate, the resistance increase rate and the capacitance attenuation rate are calculated according to the sampling duration and the three key parameters of voltage, internal resistance and capacitance, and the three indexes are taken as the comprehensive characteristics describing the battery aging degree. The innovation of the feature extraction method is that the sampling duration of the time dimension is introduced, which can more reasonably reflect the change trend of the battery parameter with time; and the change rate of the parameter is used as the feature, which can eliminate the influence of the inherent difference of different batteries.

[0022] Optionally, the preset period is divided into a plurality of standard time periods; a feature matrix of each standard time period is generated according to the driving behavior characteristics and the battery aging characteristics in each standard time period; a feature vector of each standard time period is obtained by splicing the features of each row in each feature matrix in time sequence; and a battery health feature vector of the energy storage battery in the preset period is determined according to the feature vectors of each standard time period.

[0023] By adopting the technical solution, the time evolution law of the battery health state can be well captured by the time segmentation method. The driving behavior and the battery aging characteristics are combined in each time period, which can comprehensively describe the internal and external factors affecting the battery attenuation in the time period. The process of splicing the time period feature vectors ensures that the feature vector can reflect the causal relationship and dynamic change trend in time, and the obtained comprehensive battery health feature vector can accurately reflect the change of the battery health state in the entire evaluation period, laying a data foundation for the subsequent SOH and RUL prediction.

[0024] Optionally, the battery health feature vector is divided into training set data and validation set data according to a preset proportion, and the training model is trained according to the training set data and the validation set data until a preset iteration termination condition is reached, the preset iteration termination condition being that the number of iterations reaches a preset threshold or the loss function of the training model converges; and the training model reaching the preset iteration termination condition is determined as the SOH prediction model.

[0025] By adopting the technical scheme, the constructed battery health feature vector is divided into training set data and validation set data according to a preset proportion. Then, the prediction model is trained based on the training set data, and the generalization ability of the model on unseen data is evaluated by using the validation set data, and the stopping of the training is controlled according to the preset iteration termination condition (which can be that the number of iterations reaches a threshold or the model loss function converges), and finally the model parameters when the termination condition is reached are determined as the final SOH prediction model. This alternating iterative training strategy based on the training set and the validation set can well improve the generalization performance of the model and prevent overfitting; the validation set plays a role in monitoring the performance of the model and provides a basis for early stopping; taking the convergence of the loss function as one of the termination conditions can ensure that the model reaches excellent convergence performance.

[0026] In a second aspect of the present application, a SOH and RUL prediction system of an energy storage battery is provided, the system comprising:

[0027] a parameter acquisition module configured to acquire battery parameters of the energy storage battery and driving parameters of an electric vehicle corresponding to the energy storage battery;

[0028] a SOH prediction module configured to align timestamps of the driving behavior feature and the battery aging feature within a preset period, and construct a battery health feature vector of the energy storage battery within the preset period according to the driving behavior feature and the battery aging feature; input the battery health feature vector into a training model to obtain a SOH prediction model of the energy storage battery, and predict a current battery health value of the energy storage battery based on the SOH prediction model;

[0029] a RUL prediction module configured to predict a current remaining battery life of the energy storage battery according to the current battery health value of the energy storage battery, a cumulative use time length, and a standard battery life.

[0030] In a third aspect of the present application, an electronic device is provided, comprising a memory, a processor, and a program stored in the memory and executable on the processor, which can be loaded and executed by the processor to implement a SOH and RUL prediction method of an energy storage battery.

[0031] In a fourth aspect of the present application, a computer readable storage medium is provided, which stores a computer program, and the computer program is executed by a processor to enable the processor to implement a SOH and RUL prediction method of an energy storage battery.

[0032] To sum up, the one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0033] By adopting the technical solutions of the present application, the battery parameters and the vehicle driving parameters are acquired, then the driving behavior features are determined based on the driving parameters, and the battery aging features are determined based on the battery operation data. Then the driving behavior features and the battery aging features are aligned in the time dimension, and a comprehensive feature vector describing the battery health state is constructed. The feature vector is input into the training model for training to obtain the SOH prediction model, and based on this, the current SOH of the energy storage battery, i.e. the battery health value, is predicted, and combined with the predicted SOH, the cumulative use time and the standard battery life, the current RUL, i.e. the remaining battery life, is predicted. The battery parameters of the battery itself affecting the battery aging and the driving parameters of the external electric vehicle corresponding to the energy storage battery are fused, and the influence of driving habits and other use conditions on the battery attenuation is considered in multiple dimensions, thereby improving the accuracy of SOH and RUL prediction. BRIEF DESCRIPTION OF DRAWINGS

[0034] Figure 1 is a flow diagram of a SOH and RUL prediction method of an energy storage battery provided by the embodiments of the present application;

[0035] Figure 2 is a structural diagram of a SOH and RUL prediction system of an energy storage battery disclosed by the embodiments of the present application;

[0036] Figure 3 is a structural diagram of an electronic device disclosed by the embodiments of the present application.

[0037] The following items are explained: 300, electronic device; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. DETAILED DESCRIPTION

[0038] In order for those skilled in the art to better understand the technical solutions in the present specification, the technical solutions in the embodiments of the present specification will be described clearly and completely below in conjunction with the drawings in the embodiments of the present specification. Obviously, the described embodiments are only a part of the embodiments of the present application, not all the embodiments.

[0039] In the description of the embodiments of the present application, the words such as "for example" or "for instance" are used to represent an example, illustration or description. Any embodiment or design scheme described as "for example" or "for instance" in the embodiments of the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. Rather, the words such as "for example" or "for instance" are intended to present the relevant concept in a specific manner.

[0040] In the description of the embodiments of the present application, the term "a plurality of" means two or more. For example, a plurality of systems means two or more systems, and a plurality of screen terminals means two or more screen terminals. In addition, the terms "first", "second", etc. are used only for the purpose of description and should not be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Therefore, the features defined with "first", "second" can explicitly or implicitly include one or more of the features. The terms "include", "contain", "have" and their variants mean "include but are not limited to", unless otherwise specifically emphasized.

[0041] The embodiments of the present application provide a SOH and RUL prediction method of an energy storage battery. In one embodiment, please refer to Figure 1 , Figure 1 is a flowchart of the SOH and RUL prediction method of the energy storage battery provided by the embodiments of the present application. The method can be implemented by relying on a computer program, which can be integrated in an application or run as an independent tool application. The method can also be implemented by relying on a single-chip microcomputer or run on a SOH and RUL prediction system of the energy storage battery based on the von Neumann system. Specifically, the method can include the following steps:

[0042] Step 101: Obtain the battery parameters of the energy storage battery and the driving parameters of the corresponding electric vehicle of the energy storage battery.

[0043] Among them, the battery parameters refer to the data directly reflecting the working state of the battery, which can be understood as the physical and chemical properties of the battery such as voltage, internal resistance and capacitance in the embodiments of the present application, which are used to reflect the health state and electrochemical process of the battery.

[0044] The driving parameters refer to the data reflecting the use and driving conditions of the electric vehicle, which can be understood as the parameters such as driving distance, driving time, braking times, average speed, etc. in the embodiments of the present application, which are used to reflect the influence of the user's driving habits on the battery.

[0045] Specifically, in order to accurately predict the state of health (SOH) and the remaining useful life (RUL) of the energy storage battery, the influence of the actual driving condition of the user on the battery needs to be considered. The battery parameters of the energy storage battery, including voltage, current, temperature, etc., which directly reflect the working state of the battery, and the driving parameters of the corresponding electric vehicle, including driving distance, driving time, braking frequency, average speed, etc. The driving parameters can be obtained by collecting the vehicle-mounted sensors, which reflect the driving habits of the user. The purpose of obtaining the parameters of the energy storage battery and the driving parameters is to establish a battery health feature vector in the subsequent process, fully considering the influence of the battery itself and the use factors on the battery health state. For example, frequent high-speed acceleration will accelerate the degradation of the battery; long-term high-temperature conditions will also reduce the capacity of the battery. Comprehensive analysis of the two types of parameters can make the prediction result more accurately reflect the actual health status of the battery.

[0046] Step 102: based on the driving parameters, determine the driving behavior characteristics of the electric vehicle, and based on the battery parameters, determine the battery aging characteristics of the energy storage battery.

[0047] Among them, the driving behavior characteristics refer to the characteristic parameters reflecting the driving habits of the driver, which can be understood in the embodiments of the present application as emergency braking behavior, high-speed driving behavior, and long-distance driving behavior, etc., for reflecting the influence of the driving mode of the driver on the battery health state.

[0048] The battery aging characteristics refer to the characteristic parameters reflecting the performance degradation of the battery, which can be understood in the embodiments of the present application as voltage decay rate, internal resistance growth rate, and capacitance decay rate, etc., for quantitatively describing the decline of the battery capacity and power performance.

[0049] Specifically, on the basis of obtaining the energy storage battery parameters and the driving parameters, the battery health characteristics are further extracted, and the purpose of this step is to obtain characteristics that can fully reflect the battery health state, laying a foundation for constructing the battery health feature vector. According to the driving time, braking frequency and average speed in the driving parameters, etc., the driving behavior characteristics of the electric vehicle can be determined, mainly including: emergency braking behavior, high-speed driving behavior and long-distance driving behavior, etc. The extraction method of these behavior characteristics can pre-set corresponding determination conditions and threshold values, when the driving parameters meet the determination conditions, the corresponding behavior characteristics can be determined. For example, when the braking frequency exceeds a certain number / km, it is determined as emergency braking behavior, which can reflect the influence of the actual use of the user on the battery. And according to the time series data of the battery operating data of the energy storage battery, such as voltage, internal resistance, and capacitance, the change rates of these parameters can be calculated to determine the battery aging characteristics, such as the decay rate of the voltage, the growth rate of the internal resistance, and the decay rate of the capacitance, which can well quantify the health degradation state of the battery.

[0050] On the basis of the above-mentioned embodiments, as an optional embodiment, in step 102: based on the driving parameters, the driving behavior characteristics of the electric vehicle are determined, and this step can further include the following steps:

[0051] Step 201: According to the driving time, braking frequency and driving speed in the driving parameters, the driving behaviors of the electric vehicle are determined, and the driving behaviors include emergency braking behavior, high-speed driving behavior and long-distance driving behavior.

[0052] Among them, the driving time represents the time length of a single driving, which is used to judge the influence of long-time driving. The braking frequency represents the number of braking times per driving distance, which is used to judge the influence of frequent starting and stopping in urban road conditions. The driving speed represents the average speed of driving, which is used to judge the influence of high-speed driving.

[0053] Driving behavior refers to the operation mode of the driver during driving, which can be understood as emergency braking behavior, high-speed driving behavior and long-distance driving behavior in the embodiments of the present application, and is used to reflect the influence of the driving habits of the driver on the battery health state. These driving behaviors can be obtained by judging the driving parameters, for example, the emergency braking behavior reflects the behavior habit of frequent braking in urban road conditions. The high-speed driving behavior reflects the behavior habit of long-time high-speed driving. The long-distance driving behavior reflects the behavior habit of long-distance driving.

[0054] Specifically, in order to fully consider the influence of the driving habits of the user on the battery health, it is necessary to determine the driving behavior characteristics according to the driving parameters. The purpose of this step is to extract the behavior characteristics which have important influence on the battery state from the driving parameters. According to the driving time, braking frequency and average speed, different driving behaviors are judged. If the driving time exceeds a preset threshold, such as more than 2 hours, it can be judged as long-distance driving behavior. Long-distance driving will consume more power and increase the burden of the battery. If the number of braking times per unit distance exceeds a preset value, such as more than 20 times per kilometer, it can be judged as emergency braking behavior. Frequent braking reflects the urban road conditions and also increases the mechanical fatigue of the battery. If the average speed exceeds a preset speed threshold, such as more than 80 kilometers per hour, it can be judged as high-speed driving behavior. High-speed driving requires more power, which accelerates the performance degradation of the battery. According to these behavior characteristics, the working state of the battery under different working conditions can be reflected.

[0055] On the basis of the above-mentioned embodiments, as an optional embodiment, in step 201: according to the driving time, braking frequency and driving speed in the driving parameters, the driving behaviors of the electric vehicle are determined, and this step can further include the following steps:

[0056] Step 211: If the driving time is greater than or equal to a preset time length, the long-distance driving behavior is determined as the driving behavior of the electric vehicle.

[0057] Specifically, to accurately determine the long-distance driving behavior, it is necessary to determine according to the driving time and the preset time threshold. The purpose of determining the long-distance driving behavior is to identify the battery effect caused by long-time driving. Long-time driving consumes more power and increases the chemical degradation of the battery. The driving time data in the driving parameters is obtained, and then compared with the preset time threshold, which can be set according to the actual situation, for example, set to 2 hours. If the time duration of one detected driving is greater than or equal to 2 hours, it can be determined that the driving process is a long-distance driving behavior. The final long-distance driving behavior identifier will be part of the driving behavior characteristics, reflecting the impact of long-time battery work, combined with the battery aging characteristics, the impact of long-distance driving on the battery health state can be evaluated, and the accuracy of SOH and RUL prediction can be improved.

[0058] Step 221: If the brake frequency is greater than or equal to the preset frequency, determine the emergency braking behavior as the driving behavior of the electric vehicle.

[0059] Specifically, to accurately determine the emergency braking behavior, it is necessary to determine according to the brake frequency and the preset frequency threshold. The purpose of determining the emergency braking behavior is to identify the battery effect caused by frequent braking. Frequent braking increases the number of charge and discharge cycles of the battery, and also brings greater mechanical impact to the battery. The number of brakes in the unit mileage is counted to calculate the brake frequency, and then compared with the preset frequency threshold, which can be set according to the actual situation, for example, set to 20 times of braking per kilometer. If the detected brake frequency is greater than or equal to 20 times per kilometer, it can be determined as emergency braking behavior. The final emergency braking identifier will be part of the driving behavior characteristics, reflecting the impact of frequent braking on the battery.

[0060] Step 231: If the driving speed is greater than or equal to the preset speed, determine the high-speed driving behavior as the driving behavior of the electric vehicle.

[0061] Specifically, to accurately determine the high-speed driving behavior, it is necessary to determine according to the driving speed and the preset speed threshold. The purpose of determining the high-speed driving behavior is to identify the battery effect caused by long-time high-speed driving. High-speed driving requires the battery to continuously output large power, which increases the burden of the battery and shortens the service life of the battery. The average speed data in the driving parameters is obtained, and then compared with the preset speed threshold. The preset speed threshold can be set according to the actual situation, for example, set to 80 kilometers per hour. If the detected average speed is greater than or equal to 80 kilometers per hour, it can be determined that the driving process is a high-speed driving behavior. The final high-speed driving behavior identifier will be part of the driving behavior characteristics, reflecting the impact of high-speed driving on the battery.

[0062] Step 202: generating a driving behavior time sequence of the electric vehicle according to a sampling period of each driving behavior and driving parameter, and taking the driving behavior time sequence as the driving behavior feature.

[0063] The sampling period refers to a time interval for collecting the driving parameter, which can be understood in the embodiment of the application as a time period for collecting the driving parameter determined according to a fixed time length (for example, every 5 minutes) or a fixed driving distance (for example, every 10 kilometers), for generating the driving behavior time sequence, and reflecting the change of the driving behavior over time.

[0064] The driving behavior time sequence refers to a sequence of driving behavior data arranged in chronological order, which can be understood in the embodiment of the application as a sequence of driving behaviors identified according to the sampling period, connected in chronological order, for reflecting the influence of the long-term driving habit of the driver on the battery.

[0065] Specifically, after determining the driving behavior feature of the electric vehicle, the driving behavior time sequence needs to be generated, so as to subsequently construct the health feature vector of the battery. The purpose of generating the driving behavior time sequence is to record the change of different driving behaviors over time, and reflect the long-term driving habit of the user. The driving behavior time sequence is generated according to the different driving behaviors identified in the previous steps, in the order of the sampling period of the driving parameter. For example, the high-speed driving behavior is detected in time period 1, and the emergency braking behavior is detected in time period 2, and the following driving behavior time sequence can be constructed: [time period 1: high-speed driving; time period 2: emergency braking;...] The time period can be set as a fixed time interval, such as every 5 minutes, or a fixed driving distance, such as every 10 kilometers. By generating the driving behavior time sequence, the influence of the driving habit of the user on the battery can be reflected from the long-time dimension, as an important part of the battery health feature vector.

[0066] On the basis of the above embodiment, as an optional embodiment, in step 102: determining the battery aging feature of the energy storage battery based on the battery parameter, this step can further include the following steps:

[0067] Step 203: determining the sampling duration of the battery parameter.

[0068] The sampling duration of the battery parameter refers to a time span for collecting the battery operation parameter data, which can be understood in the embodiment of the application as a period of time covering the main service life of the battery, for example, 3 years, for obtaining time sequence data of voltage, current, temperature and the like that can sufficiently reflect the battery aging process.

[0069] Specifically, after obtaining the operating parameters of the battery, it is necessary to determine a reasonable battery parameter sampling duration to extract the aging characteristics of the battery. The purpose of determining the battery parameter sampling duration is to obtain sufficient data that can fully reflect the battery aging process. The sampling duration needs to be set neither too short nor too long. A relatively reasonable time range can be selected according to the expected service life of the battery. For example, if the expected service life of the battery is 5 years, the sampling duration can be set to 3 years to ensure that the battery aging process in the middle and later stages is covered. The efficiency of data storage and calculation processing also needs to be considered. Too long a duration will generate a large amount of redundant data, and too short a duration will not be able to observe the overall performance degradation of the battery. For example, the sampling duration of the battery parameters is set to 3 years. In this period, the voltage, current, temperature, and internal resistance parameters are collected as the basic data for extracting the battery aging characteristics.

[0070] Step 204: determining the voltage change rate of the energy storage battery according to the sampling duration and the voltage; determining the internal resistance increase rate of the energy storage battery according to the sampling duration and the internal resistance; and determining the capacitance decay rate of the energy storage battery according to the sampling duration and the capacitance.

[0071] The voltage change rate refers to the quantitative ratio of the change of the battery voltage over time. In the embodiments of the present application, it can be understood as the average decay rate of the voltage value of the battery within the sampling duration, which is used to quantitatively describe the degree of decline in the power supply performance of the battery.

[0072] The internal resistance increase rate refers to the ratio of the change of the internal resistance of the battery over time. In the embodiments of the present application, it can be understood as the average growth rate of the internal resistance value of the battery within the sampling duration, which is used to quantitatively describe the degree of decline in the chemical activity of the battery.

[0073] The capacitance decay rate refers to the ratio of the change of the capacitance of the battery over time. In the embodiments of the present application, it can be understood as the average decay rate of the capacitance value of the battery within the sampling duration, which is used to quantitatively describe the degree of decline in the energy storage performance of the battery.

[0074] Specifically, after obtaining the time series data of the battery parameters, it is necessary to determine the aging characteristics of the battery based on these data. The purpose of determining the voltage change rate, internal resistance increase rate and capacitance decay rate is to extract characteristic parameters that can quantitatively describe the degree of battery aging. In the set sampling time length of the battery parameters, the voltage, internal resistance and capacitance time series data of the battery are collected, and then the average decay rate of the voltage, the average growth rate of the internal resistance, and the average decay rate of the capacitance are calculated. The calculation method is: voltage change rate = (initial voltage - final voltage) / sampling time length, internal resistance increase rate = (final internal resistance - initial internal resistance) / sampling time length, and capacitance decay rate = (initial capacitance - final capacitance) / sampling time length. The change rate of these parameters can directly reflect the degree of performance degradation of the battery, so they are determined as the aging characteristics of the battery. The obtained aging characteristics will be combined with the user behavior characteristics to form a feature vector of the battery health state, which is used to evaluate the SOH and remaining life of the battery, and to realize accurate monitoring and prediction of the battery health.

[0075] Step 205: taking the voltage change rate, internal resistance increase rate and capacitance decay rate as the battery aging characteristics of the energy storage battery.

[0076] Specifically, after obtaining the voltage change rate, internal resistance increase rate and capacitance decay rate, they are integrated into the aging characteristics of the battery. The purpose of determining these parameters as the aging characteristics of the battery is to obtain a quantitative index that can reflect the overall health status of the battery. The voltage change rate reflects the degradation of the battery's power supply performance, the internal resistance increase rate reflects the degradation of the battery's chemical activity, and the capacitance decay rate reflects the degradation of the battery's energy storage performance. These three parameters can measure the health of the battery from different aspects, and their combination into a feature vector can comprehensively reflect the aging condition of the battery.

[0077] Step 103: aligning the timestamps of the driving behavior characteristics and the battery aging characteristics in the preset period, and constructing a battery health feature vector of the energy storage battery in the preset period according to the driving behavior characteristics and the battery aging characteristics.

[0078] Wherein, the timestamp refers to an identifier that records the time of an event, which in the embodiments of the present application can be understood as a specific time point indicating that the driving behavior characteristics and the battery aging characteristics are detected, and is used to align them in the same time period to construct the health feature vector of the battery.

[0079] The battery health feature vector refers to a comprehensive feature expression containing battery use environment information and its own state information, which in the embodiments of the present application can be understood as the combination of the driving behavior characteristics and the battery aging characteristics aligned in the same time period, and is used to comprehensively reflect the health status of the battery as the input of the battery health evaluation and life prediction model.

[0080] The preset period refers to a time range for extracting the battery health feature vector, which can be understood in the embodiments of the application as a fixed time span, for example, 1 month, used for collecting and aligning the driving behavior features and the battery aging features in the period to construct the feature vector reflecting the health status of the battery in the period.

[0081] Specifically, after obtaining the driving behavior features and the battery aging features, the two features need to be aligned in the same time period to construct the health feature vector of the battery. The purpose of time alignment is to make the driving behavior features and the battery aging features correspond to each other, reflecting the use environment and health status of the battery in the same time period. A fixed period, for example, 1 month, can be set in advance. Then, in this period, the driving behavior time series and the battery aging parameter time series are extracted respectively to ensure that the time stamps of the two are aligned. Taking January 1 to January 31 as a period, the driving behavior features include features of 31 time periods, and the battery aging features also include feature values of each day in the month. In the same time period, the driving behavior features and the battery aging features are combined to form the health feature vector of the battery in the period, for example: [behavior on January 1, aging feature on January 1;...; behavior on January 31, aging feature on January 31]. The health feature vector contains information of the use environment and the state of the battery, and can comprehensively reflect the health degree of the battery. The vector is used as input for the SOH evaluation and RUL prediction model, which can improve the accuracy of the results.

[0082] On the basis of the above embodiments, as an optional embodiment, in step 103, the battery health feature vector of the energy storage battery in the preset period is constructed according to the driving behavior features and the battery aging features. This step can further include the following steps:

[0083] Step 301: dividing the preset period into a plurality of standard time periods; generating a feature matrix of each standard time period according to the driving behavior features and the battery aging features in each standard time period.

[0084] The standard time period refers to a sub-time interval obtained by uniformly dividing the preset period, which can be understood in the embodiments of the application as a daily time period obtained by equally dividing a month, used for extracting the battery health features in each time period and constructing a standardized feature matrix to provide structured samples for the training of the health evaluation model.

[0085] The feature matrix refers to a matrix expression of the battery health features arranged in a unified format, which can be understood in the embodiments of the application as a matrix formed by arranging the driving behavior features and the battery aging features of each standard time period in a fixed order, used as a training sample of the health evaluation model to facilitate the model to learn the health status change rule of the battery in different time periods.

[0086] Specifically, after obtaining the battery health feature vector of the preset period, it is necessary to further construct a feature matrix of the standard time period. The purpose of dividing the preset period into standard time periods is to obtain a regular and comparable feature representation, and to provide structured samples for model training. The preset period of one month can be divided into multiple standard time periods at equal intervals, for example, one period per day, and then in each standard time period, the driving behavior features and battery aging features of the period are extracted and arranged in a fixed order to form a feature matrix. In this way, a regular matrix form sample can be obtained, each row representing the battery health features of a period, and a standardized feature matrix can be obtained, which can be conveniently used as a training sample for the model to improve the training effect. At the same time, it is also convenient for comparative analysis of battery health features in different time periods. The division of standard time periods and the generation of feature matrices provide effective samples for the training of health evaluation and prediction models, which can improve the accuracy of battery state detection.

[0087] Step 302: According to the time sequence, splice the features of each row in each feature matrix to obtain the feature vector of each standard time period.

[0088] Wherein, the time sequence refers to the order of events or features arranged according to the occurrence time, which can be understood in the embodiments of the present application as the time sequence of the rows in the standard time period feature matrix, which is used to splice the feature vectors according to the time sequence, so that the feature vectors retain dynamic time information and can reflect the process of the change of the battery health state over time.

[0089] The features of each row in the feature matrix refer to the combination of driving behavior features and battery aging features in the same standard time period, which can be understood in the embodiments of the present application as the sequence of feature items in the feature matrix representing a standard time period, which is used to splice according to the time sequence to construct a long sequence feature vector containing complete features of each period.

[0090] The feature vector refers to the integration of multiple features into a fixed order one-dimensional vector representation, which can be understood in the embodiments of the present application as a one-dimensional feature sequence containing complete time period information obtained by splicing each row of the standard time period feature matrix, which is used to provide a suitable sample input form for the battery health evaluation and prediction model based on deep learning.

[0091] Specifically, after obtaining the feature matrix of the standard time period, it is necessary to further construct a feature vector containing complete time information. It is a reasonable method to splice each row of the matrix in time sequence. The purpose of this is to obtain a long sequence feature vector containing dynamic time information, which can reflect the trajectory of the battery health state changing over time. This vector not only retains the integrity of the features of each time period, but also embodies the sequence of time, and is a suitable sample form for the model to learn the aging law of the battery. According to the time labels of each row of the feature matrix, the time sequence is confirmed, and then the features are spliced in time sequence. The driving behavior features and battery aging features of the same period are combined to construct the feature expression of the period. Each row is spliced in turn until the traversal is completed. Finally, a long sequence vector containing features of the whole time period is formed. Through the time sequence splicing of the matrix row features, the feature vector obtained not only maintains the health state features of the battery in each standard time period, but also reflects that the battery aging is a time dynamic process.

[0092] Step 303: determining the battery health feature vector of the energy storage battery in the preset period according to the feature vectors of each standard time period.

[0093] Specifically, after obtaining the feature vector of the standard time period, it is necessary to further determine the battery health feature vector reflecting the whole preset period. The purpose is to obtain a feature expression containing complete information of the preset period, which can comprehensively reflect the change of the battery health state in this stage as the input of the battery health evaluation. The feature vectors constructed in each standard time period are combined in time sequence to construct a long sequence feature vector containing all standard time periods as the final battery health feature vector. This feature vector includes the health status and change trajectory of the battery in different time periods in the preset period, and can fully reflect the overall health characteristics of the battery in this period.

[0094] Step 104: inputting the battery health feature vector into the training model to obtain the SOH prediction model of the energy storage battery, and predicting the current battery health value of the energy storage battery based on the SOH prediction model.

[0095] The training model refers to a prediction model established by a machine learning algorithm. In the embodiments of the present application, it can be understood as a data-driven prediction model based on the battery health feature vector, which is used to learn the law of the change of the battery health state and realize intelligent evaluation and prediction of the battery health index SOH.

[0096] The SOH prediction model refers to a machine learning model for predicting the battery health state (State of Health). In the embodiments of the present application, it can be understood as an LSTM network model trained based on the battery health feature vector, which is used to predict the SOH value of the battery in the future period and evaluate the health state of the battery.

[0097] The battery health value refers to an index for evaluating the overall health status of the battery, which can be understood as a predicted battery SOH value in the embodiments of the present application, and is used to judge the health degree and remaining life of the battery.

[0098] Specifically, after the vector fully reflecting the battery health characteristics is constructed, the prediction model needs to be further trained based on the vector to realize the evaluation of the battery health status. The purpose is to realize intelligent prediction of the battery health value SOH through a machine learning model, and to provide a data-driven battery health management scheme. The constructed battery health feature vector is input as a sample, and a sequential model such as LSTM is used for training. The model can learn the battery health evolution law through the feature vector. The trained model contains both the battery use environment information and the time sequence mode of battery aging. In actual prediction, the latest period of battery health feature vectors is monitored and obtained, and the trained SOH prediction model is input. The model can give the current battery health value of the battery, i.e., the SOH of the energy storage battery, reflecting the health status of the battery.

[0099] On the basis of the above-mentioned embodiments, as an optional embodiment, in step 104: the battery health feature vector is input into the training model to obtain the SOH prediction model of the energy storage battery. This step can further include the following steps:

[0100] Step 401: dividing the battery health feature vector into training set data and validation set data according to a preset ratio, and training the training model according to the training set data and the validation set data until a preset iteration termination condition is reached. The preset iteration termination condition is that the number of iterations reaches a preset threshold or the loss function of the training model converges; and determining the training model that reaches the preset iteration termination condition as the SOH prediction model.

[0101] Specifically, the loss function of the training model refers to an index for measuring the fitting effect of the model on the training data, which can be understood in the embodiments of the present application as the error calculated by the machine learning model in the iteration process for the training data.

[0102] The number of iterations refers to the number of times of gradient update optimization of the training data in the model training process, which can be understood in the embodiments of the present application as the number of times of repeatedly adjusting the model parameters using the training data set during the training of the model, and is used to control the number of rounds of model training, achieving a balance between training effect and calculation cost.

[0103] Specifically, after obtaining the vector data reflecting the battery health characteristics, a generalizable prediction model is needed to be obtained by splitting the training data and validation data and iterating the training. The purpose is to fit the battery health change rule based on the training data, and improve the prediction ability of the model on new data through the validation data, to obtain a battery health evaluation model that learns both feature patterns and has generalization ability. For example, the feature vectors are divided into training set and validation set in the ratio of 8:2. Then load the machine learning model, iterate the model with training data, and constantly optimize the learning of the battery health evolution pattern in the feature vector. At the same time, the validation set data is used to evaluate the prediction effect of the model on new data during the iteration process. When the loss function converges or reaches the preset iteration number, the training is stopped, and the final model that fits well on the training data and has strong generalization ability on new data is obtained. In this way, through the iterative model optimization of training and validation, a battery health evaluation model that represents both training data and has generalization ability can be obtained.

[0104] Step 105: predicting the current remaining battery life of the energy storage battery according to the current battery health value of the energy storage battery, the cumulative use time length, and the standard battery life.

[0105] The cumulative use time length refers to the total use time of the battery from the factory to the current time, which can be understood in the embodiment of the application as the total running time accumulated in chronological order after the battery is put into use, and is used to reflect the use history of the battery, judge the consumption degree of the battery, and predict the remaining life of the battery.

[0106] The standard battery life refers to the expected total time length of the battery from the factory to the scrap under normal use conditions, which can be understood in the embodiment of the application as the normal use cycle time of the battery product specified in the technical specification.

[0107] The remaining battery life refers to the expected remaining working time of the battery from the current time to the time when it cannot continue to be used normally, which can be understood in the embodiment of the application as the remaining time that the battery can be used from the current time based on the battery health state evaluation and the used time length calculation, i.e. the current RUL of the energy storage battery.

[0108] Specifically, to achieve accurate assessment of the remaining battery life, it is necessary to consider the current health state, usage history and standard life for prediction analysis. The purpose is to accurately judge the remaining available time of the battery, which can better guide the scientific use and planned maintenance of the battery. The SOH health state value of the battery at the current time is obtained, which can reflect the degree of battery consumption; then the cumulative usage time of the battery so far is counted to judge the consumption history of the battery; the standard life cycle of the battery is referred to, the standard life used proportion is determined combined with the SOH value, and the influence of various factors on the remaining life is considered by a pre-set formula to obtain the specific time that the battery can be reused from the current time.

[0109] On the basis of the above embodiment, as an optional embodiment, in step 105, the current remaining battery life of the energy storage battery is predicted according to the current battery health value of the energy storage battery, the cumulative usage time and the standard battery life. This step can also include the following steps:

[0110] Step 501: Substitute the current battery health value of the energy storage battery, the cumulative usage time and the standard battery life into the preset battery life prediction formula to obtain the current remaining battery life of the energy storage battery; wherein the preset battery life prediction formula is:

[0111]

[0112] In the formula, R represents the current remaining battery life of the energy storage battery, T life represents the standard life of the energy storage battery, SOH represents the current battery health value of the energy storage battery, f fast represents the aging factor of the energy storage battery in the fast charging mode, p fast represents the fast charging proportion of the energy storage battery, f slow represents the aging factor of the energy storage battery in the slow charging mode, p slow represents the slow charging proportion of the energy storage battery, T used represents the current cumulative usage time of the energy storage battery.

[0113] The preset battery life prediction formula refers to a mathematical formula for calculating the current remaining battery life of the energy storage battery. In the embodiments of the present application, the preset battery life prediction formula can be understood as a multiple analysis model containing the current battery health value of the energy storage battery, the cumulative usage time and the standard battery life and other factors. The preset battery life prediction formula is used for quantitative calculation and evaluation of the current remaining battery life of the energy storage battery, and the current remaining battery life of the energy storage battery can be calculated by substituting the actual detection data.

[0114] Specifically, to evaluate the remaining available time of the battery, it is necessary to calculate based on the standard life prediction formula, the purpose is to use the pre-established mathematical formula, input the real situation data of the battery, intelligently predict the remaining battery life of the battery. The SOH health state value monitored at the current time of the battery is obtained, and the cumulative working time of the battery is also counted, and the industrial standard life cycle data of the battery product is prepared. Then the above three factors are substituted into the preset life prediction formula in turn, and the algorithm is executed, and finally the RUL value of the battery from the current time, that is, the remaining battery life, can be automatically obtained. Compared with artificial experience estimation, the standard formula algorithm can realize efficient and automatic prediction of a large number of remaining battery life, and the result reflects the real health and consumption state of the battery, so that the subsequent use plan of the battery is more accurate and reliable.

[0115] The formula consists of three parts, the first part represents the influence function of the standard battery life of the energy storage battery and the battery health value on the remaining battery life. Among them, T life represents the standard life of the energy storage battery, which is the total use time that the battery is expected to achieve under ideal conditions, which is an estimated value provided by the manufacturer based on the battery performance degradation under standard test conditions. SOH represents the current battery health value of the energy storage battery, which is obtained based on the driving behavior of the electric vehicle and the battery state. The calculation result of this part represents the ideal life of the battery under the current health state of the battery, which is the adjustment of the expected life when the health state of the battery is not lost. If the health state of the battery decreases, that is, the SOH battery health value decreases, it means that the effective life of the battery also decreases accordingly.

[0116] The second part represents the influence function of the charging mode of the energy storage battery on the remaining battery life, including the fast charging mode and the slow charging mode, f fast represents the aging factor of the energy storage battery in the fast charging mode, that is, the proportion factor of the fast charging mode on the accelerated attenuation of the battery life, which describes the additional damage of the fast charging mode to the battery health compared with the normal charging condition. Fast charging will accelerate the chemical aging process of the battery due to large current and high temperature, thereby shortening the battery life. fast represents the time proportion of the battery using fast charging mode during the entire use period. The higher this proportion means that the battery experiences fast charging more frequently, and is more likely to be affected by the negative effects of fast charging mode. slow represents the proportion factor of the slow charging mode on the accelerated attenuation of the battery life, usually, this factor is low, because the slow charging has relatively small effect on the battery, and the slow charging mode is generally considered to be more gentle to the battery, and has less effect on the overheat or other fast attenuation of the battery. slowrepresents the proportion of time the battery spends in slow charging mode over its entire lifetime. A higher slow charging proportion generally helps maintain battery health and slow down the aging process of the battery. This part combines the type of battery charging mode, i.e. fast and slow charging, and its frequency of use, i.e. proportion, as well as the impact of these modes on battery life, i.e. the acceleration aging factor. The product of each item represents the specific contribution of this charging mode to the overall health and life of the battery. Fast charging generally has a greater impact on the overall health of the battery due to its higher aging factor.

[0117] The third part represents the function of the current cumulative usage time of the energy storage battery and the standard battery life on the remaining battery life. This part calculates the proportion of the remaining battery life, which represents the proportion of the used life subtracted from the total expected life, thereby obtaining the proportion of the remaining life. If T used approaches T life , this proportion will approach 0, indicating that the battery is approaching the end of its expected life. Conversely, if T used is much smaller than T life , this proportion will approach 1, meaning that the battery still has most of its life to use.

[0118] In summary, the formula f fast ×p fast +f slow ×p slow represents the overall impact of charging mode on battery life, while 1- represents the proportion of the remaining battery life. The product of these two gives the adjusted remaining life proportion of the battery under the influence of usage and charging mode, combined with T life ×SOH, which represents the theoretical maximum life of the battery under the current state of health. Through this preset battery life prediction formula, the remaining use time of the battery can be more accurately predicted, helping to manage and optimize the use of the battery.

[0119] Referring to Figure 2 , an SOH and RUL prediction system for an energy storage battery is provided, the system comprising: a parameter acquisition module, a feature determination module, an SOH prediction module, and an RUL prediction module, wherein:

[0120] The parameter acquisition module is configured to acquire battery parameters of the energy storage battery and driving parameters of an electric vehicle corresponding to the energy storage battery.

[0121] The feature determination module is configured to determine driving behavior features of the electric vehicle based on the driving parameters, and determine battery aging features of the energy storage battery based on the battery parameters.

[0122] The SOH prediction module is configured to align timestamps of the driving behavior feature and the battery aging feature within a preset period, and construct a battery health feature vector of the energy storage battery within the preset period according to the driving behavior feature and the battery aging feature; input the battery health feature vector into the training model to obtain an SOH prediction model of the energy storage battery, and predict the current battery health value of the energy storage battery based on the SOH prediction model.

[0123] The RUL prediction module is configured to predict the current remaining battery life of the energy storage battery according to the current battery health value of the energy storage battery, the cumulative use time length, and the standard battery life.

[0124] On the basis of the above embodiment, the RUL prediction module is further configured to substitute the current battery health value of the energy storage battery, the cumulative use time length, and the standard battery life into a preset battery life prediction formula to obtain the current remaining battery life of the energy storage battery; wherein the preset battery life prediction formula is:

[0125]

[0126] In the formula, R represents the current remaining battery life of the energy storage battery, T life represents the standard life of the energy storage battery, SOH represents the current battery health value of the energy storage battery, f fast represents the aging factor of the energy storage battery in the fast charging mode, p fast represents the fast charging proportion of the energy storage battery, f slow represents the aging factor of the energy storage battery in the slow charging mode, p slow represents the slow charging proportion of the energy storage battery, T used represents the current cumulative use time length of the energy storage battery.

[0127] On the basis of the above embodiment, the feature determination module is further configured to determine a plurality of driving behaviors of the electric vehicle according to the driving time length, the braking frequency, and the driving speed in the driving parameters, the driving behaviors including an emergency braking behavior, a high-speed driving behavior, and a long-distance driving behavior; generate a driving behavior time sequence of the electric vehicle according to the sampling time period of each driving behavior and the driving parameter, and take the driving behavior time sequence as the driving behavior feature.

[0128] On the basis of the above embodiment, the feature determination module is further configured to determine the long-distance driving behavior as the driving behavior of the electric vehicle if the driving time length is greater than or equal to a preset time length; determine the emergency braking behavior as the driving behavior of the electric vehicle if the braking frequency is greater than or equal to a preset frequency; and determine the high-speed driving behavior as the driving behavior of the electric vehicle if the driving speed is greater than or equal to a preset speed.

[0129] On the basis of the above-mentioned embodiments, the feature determination module is further configured to determine a sampling duration of the battery parameter; determine a voltage change rate of the energy storage battery according to the sampling duration and the voltage; determine an internal resistance increase rate of the energy storage battery according to the sampling duration and the internal resistance; determine a capacitance attenuation rate of the energy storage battery according to the sampling duration and the capacitance; and take the voltage change rate, the internal resistance increase rate and the capacitance attenuation rate as the battery aging features of the energy storage battery.

[0130] On the basis of the above-mentioned embodiments, the SOH prediction module is further configured to divide the preset period into a plurality of standard time periods; generate a feature matrix of each standard time period according to the driving behavior features and the battery aging features in each standard time period; splice the features of each row in each feature matrix in time sequence to obtain a feature vector of each standard time period; and determine a battery health feature vector of the energy storage battery in the preset period according to the feature vectors of the standard time periods.

[0131] On the basis of the above-mentioned embodiments, the SOH prediction module is further configured to divide the battery health feature vector into training set data and validation set data according to a preset proportion, and train the training model according to the training set data and the validation set data until a preset iteration termination condition is reached, the preset iteration termination condition being that the number of iterations reaches a preset threshold or the loss function of the training model converges; and determine the training model that reaches the preset iteration termination condition as the SOH prediction model.

[0132] It should be noted that: the apparatus provided in the above-mentioned embodiments, in realizing its functions, is only exemplified by the division of the above-mentioned functional modules, and in actual application, the above-mentioned functions can be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the apparatus and method embodiments provided in the above-mentioned embodiments belong to the same concept, and the specific implementation process is detailed in the method embodiments, which will not be described here.

[0133] The present application also discloses an electronic device. Referring to Figure 3 , Figure 3 is a structural schematic diagram of an electronic device disclosed by the embodiments of the present application. The electronic device 300 can include at least one processor 301, at least one network interface 304, a user interface 303, a memory 305, and at least one communication bus 302.

[0134] The communication bus 302 is configured to realize the connection and communication between the components.

[0135] The user interface 303 can include a display (Display) interface and a camera (Camera) interface. Optionally, the user interface 303 can further include a standard wired interface and a wireless interface.

[0136] The network interface 304 can optionally include a standard wired interface, a wireless interface (such as a WI-FI interface).

[0137] The processor 301 can include one or more processing cores. The processor 301 connects various parts within the server through various interfaces and lines, performs various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 305, and calling data stored in the memory 305. Optionally, the processor 301 can be implemented in at least one of a hardware form of a digital signal processing (DSP), a field-programmable gate array (FPGA), and a programmable logic array (PLA). The processor 301 can be integrated with a combination of one or more of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. Among them, the CPU is mainly used to process operating systems, user interface graphs, and application programs; the GPU is used to render and draw the content to be displayed on the display screen; and the modem is used to process wireless communication. It can be understood that the above-mentioned modem can also not be integrated into the processor 301, but can be implemented by a separate chip.

[0138] The memory 305 can include a random access memory (RAM) and a read-only memory (ROM). Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 can include a program storage area and a data storage area, wherein the program storage area can store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area can store data involved in the above-mentioned various method embodiments, etc. The memory 305 can optionally be at least one storage device located away from the aforementioned processor 301. Referring to Figure 3 The memory 305 as a computer storage medium can include an operating system, a network communication module, a user interface module, and an application program of a SOH and RUL prediction method of an energy storage battery.

[0139] In Figure 3 In the electronic device 300 shown, the user interface 303 is mainly used to provide an interface for the user to input, and obtain data input by the user; and the processor 301 can be used to invoke an application program stored in the memory 305 and storing a SOH and RUL prediction method of a battery, which, when executed by one or more processors 301, causes the electronic device 300 to perform the method of one or more of the above-described embodiments. It should be noted that, for the foregoing method embodiments, in order to simply describe, they are all described as a combination of a series of actions, but those skilled in the art should know that the present application is not limited to the order of the actions described, because according to the present application, certain steps can be performed in other order or simultaneously. Secondly, those skilled in the art should know that the embodiments described in the specification all belong to preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0140] In the above embodiments, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0141] In the several embodiments provided by the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic. The division of the units is only a logical function division. There can be another division manner for actual implementation, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections between different parts can be indirect couplings or communication connections through some interfaces, devices or units, and can be electrical or other forms.

[0142] The units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0143] In addition, each functional unit in each embodiment of the present application can be integrated into a processing unit, or each unit can exist physically, or two or more units can be integrated into one unit. The above integrated unit can be realized in the form of hardware, or in the form of a software functional unit.

[0144] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable memory. Based on such understanding, the technical solutions of the present application essentially or say the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a memory and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the embodiments of the present application. The aforementioned memory includes: a U disk, a mobile hard disk, a magnetic disk or an optical disk, and various media that can store program codes.

[0145] The above are only exemplary embodiments of the present disclosure, and cannot limit the scope of the present disclosure. That is, any equivalent changes and modifications made in accordance with the teachings of the present disclosure are still within the scope of the present disclosure. Other embodiments of the present disclosure will be readily apparent to those skilled in the art upon considering the specification and practicing the true principles of the disclosure.

[0146] The present application is intended to cover any variations, uses or adaptive changes of the present disclosure that follow the general principles of the present disclosure and include common knowledge or conventional technical means in the technical field not described in the present disclosure. The specification and examples are only considered as exemplary.

Claims

1. A method of SOH and RUL prediction of an energy storage battery, characterized in that, The method comprises: obtaining battery parameters of a storage battery and driving parameters of an electric vehicle corresponding to the storage battery; determining driving behavior characteristics of the electric vehicle based on the driving parameters and determining battery aging characteristics of the storage battery based on the battery parameters; aligning timestamps of the driving behavior characteristics and the battery aging characteristics within a preset period and constructing a battery health characteristic vector of the storage battery within the preset period according to the driving behavior characteristics and the battery aging characteristics; inputting the battery health characteristic vector into a training model to obtain an SOH prediction model of the storage battery and predicting a current battery health value of the storage battery based on the SOH prediction model; predicting a current remaining battery life of the storage battery according to the current battery health value of the storage battery, a cumulative use time length and a standard battery life; the method of predicting the current remaining battery life of the storage battery according to the current battery health value of the storage battery, the cumulative use time length and the standard battery life comprises: substituting the current battery health value of the storage battery, the cumulative use time length and the standard battery life into a preset battery life prediction formula to obtain the current remaining battery life of the storage battery; wherein the preset battery life prediction formula is: ； wherein, represents the current remaining battery life of the energy storage battery, represents the standard life of the energy storage battery, represents the current battery health value of the energy storage battery, represents the aging factor of the energy storage battery in fast charging mode, represents the fast charging ratio of the energy storage battery, represents the aging factor of the energy storage battery in slow charging mode, represents the slow charging ratio of the energy storage battery, represents the current cumulative usage duration of the energy storage battery; the method of determining the driving behavior characteristics of the electric vehicle based on the driving parameters comprises: determining a plurality of driving behaviors of the electric vehicle according to driving time length, braking frequency and driving speed in the driving parameters, wherein the driving behaviors include emergency braking behavior, high-speed driving behavior and long-distance driving behavior; generating a driving behavior time sequence of the electric vehicle according to the sampling time period of each driving behavior and the driving parameters and taking the driving behavior time sequence as the driving behavior characteristics; the method of determining a plurality of driving behaviors of the electric vehicle according to driving time length, braking frequency and driving speed in the driving parameters comprises: if the driving time length is greater than or equal to a preset time length, determining the long-distance driving behavior as the driving behavior of the electric vehicle; if the braking frequency is greater than or equal to a preset frequency, determining the emergency braking behavior as the driving behavior of the electric vehicle; if the driving speed is greater than or equal to a preset speed, determining the high-speed driving behavior as the driving behavior of the electric vehicle; the method of constructing the battery health characteristic vector of the storage battery within the preset period according to the driving behavior characteristics and the battery aging characteristics comprises: dividing the preset period into a plurality of standard time periods; generating a feature matrix of each standard time period according to the driving behavior characteristics and the battery aging characteristics in each standard time period; concatenating the features of each row in each feature matrix in time sequence to obtain a feature vector of each standard time period; determining the battery health characteristic vector of the storage battery within the preset period according to the feature vectors of each standard time period. 2.The SOH and RUL prediction method of an energy storage battery according to claim 1, characterized in that, The battery parameters include voltage, internal resistance and capacitance, and the method of determining the battery aging characteristics of the storage battery based on the battery parameters comprises: Determine the sampling duration for the battery parameters; The voltage change rate of the energy storage battery is determined based on the sampling duration and the voltage. The internal resistance increase rate of the energy storage battery is determined based on the sampling duration and the internal resistance. The capacitance decay rate of the energy storage battery is determined based on the sampling duration and the capacitance. The voltage change rate, the internal resistance increase rate, and the capacitance decay rate are used as battery aging characteristics of the energy storage battery. 3.The SOH and RUL prediction method of an energy storage battery according to claim 1, characterized in that, The step of inputting the battery health feature vector into the training model to obtain the SOH prediction model of the energy storage battery includes: The battery health feature vector is divided into training set data and validation set data according to a preset ratio. The training model is trained based on the training set data and the validation set data until a preset iteration termination condition is reached. The preset iteration termination condition is that the number of iterations reaches a preset threshold or the loss function of the training model converges. The training model that reaches the preset iteration termination condition is determined as the SOH prediction model.

4. A SOH and RUL prediction system for energy storage batteries, characterized in that, The system includes: The parameter acquisition module is used to acquire the battery parameters of the energy storage battery and the driving parameters of the electric vehicle corresponding to the energy storage battery. The feature determination module is used to determine the driving behavior characteristics of the electric vehicle based on the driving parameters, and to determine the battery aging characteristics of the energy storage battery based on the battery parameters. The SOH prediction module is used to align the timestamps of the driving behavior features and the battery aging features within a preset period, and construct the battery health feature vector of the energy storage battery within the preset period based on the driving behavior features and the battery aging features; input the battery health feature vector into the training model to obtain the SOH prediction model of the energy storage battery, and predict the current battery health value of the energy storage battery based on the SOH prediction model; The RUL prediction module is used to predict the current remaining battery life of the energy storage battery based on the current battery health value, cumulative usage time and standard battery life. The step of predicting the remaining battery life of the energy storage battery based on its current battery health value, cumulative usage time, and standard battery life includes: Substitute the current battery health value, cumulative usage time and standard battery life of the energy storage battery into the preset battery life prediction formula to obtain the current remaining battery life of the energy storage battery. The preset battery life prediction formula is as follows: ； wherein, represents the current remaining battery life of the energy storage battery, represents the standard life of the energy storage battery, represents the current battery health value of the energy storage battery, represents the aging factor of the energy storage battery in fast charging mode, represents the fast charging ratio of the energy storage battery, represents the aging factor of the energy storage battery in slow charging mode, represents the slow charging ratio of the energy storage battery, represents the current cumulative usage duration of the energy storage battery; Determining the driving behavior characteristics of the electric vehicle based on the driving parameters includes: Based on the driving parameters, such as driving time, braking frequency, and driving speed, multiple driving behaviors of the electric vehicle are determined, including emergency braking behavior, high-speed driving behavior, and long-distance driving behavior. Based on the sampling time periods of each driving behavior and driving parameter, a driving behavior time series of the electric vehicle is generated, and the driving behavior time series is used as the driving behavior feature; The determination of multiple driving behaviors of the electric vehicle based on the driving parameters, including driving time, braking frequency, and driving speed, includes: If the driving duration is greater than or equal to a preset duration, the long-distance driving behavior is determined as the driving behavior of the electric vehicle; If the braking frequency is greater than or equal to a preset frequency, the emergency braking behavior is determined as the driving behavior of the electric vehicle; If the driving speed is greater than or equal to a preset speed, the high-speed driving behavior is determined as the driving behavior of the electric vehicle; The battery health feature vector of the energy storage battery in the preset period is constructed according to the driving behavior features and the battery aging features, including: dividing the preset period into multiple standard time periods; generating a feature matrix of each standard time period according to the driving behavior features and the battery aging features in each standard time period; splicing the features of each row in each feature matrix in time sequence to obtain a feature vector of each standard time period; determining the battery health feature vector of the energy storage battery in the preset period according to the feature vectors of each standard time period.

5. An electronic device, comprising: The electronic device includes a processor, a memory, a user interface, and a network interface. The memory is used to store instructions. The user interface and the network interface are used to communicate with other devices. The processor is used to execute the instructions stored in the memory to enable the electronic device to perform the SOH and RUL prediction method of the energy storage battery according to any one of claims 1-3.

6. A computer readable storage medium characterized in that, The computer-readable storage medium stores instructions that, when executed, perform the SOH and RUL prediction method of the energy storage battery according to any one of claims 1-3.

Images