CN110658460B - Battery life prediction method and device for battery pack - Google Patents
Battery life prediction method and device for battery pack Download PDFInfo
- Publication number
- CN110658460B CN110658460B CN201910935361.8A CN201910935361A CN110658460B CN 110658460 B CN110658460 B CN 110658460B CN 201910935361 A CN201910935361 A CN 201910935361A CN 110658460 B CN110658460 B CN 110658460B
- Authority
- CN
- China
- Prior art keywords
- battery pack
- battery
- life
- target
- prediction model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/367—Software therefor, e.g. for battery testing using modelling or look-up tables
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/392—Determining battery ageing or deterioration, e.g. state of health
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/60—Other road transportation technologies with climate change mitigation effect
- Y02T10/70—Energy storage systems for electromobility, e.g. batteries
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Secondary Cells (AREA)
Abstract
The application discloses a method and a device for predicting the battery life of a battery pack, which can effectively improve the accuracy of predicting the battery life of a target battery pack. The method comprises the following steps: the method comprises the steps of firstly obtaining battery use data of a target battery pack to be predicted, then inputting the battery use data serving as input data into a pre-constructed battery life prediction model so as to output the probability density that the SOH of the target battery pack reaches a preset value through the model, and further accurately predicting the battery life of the target battery according to the probability density.
Description
Technical Field
The present disclosure relates to the field of battery technologies, and in particular, to a method and an apparatus for predicting a battery life of a battery pack.
Background
In recent years, with the increasing energy crisis, new energy automobiles have become the development focus of the automobile industry in the future due to the excellent energy-saving and environment-friendly characteristics of the new energy automobiles. The battery life of the battery pack carried on the new energy automobile directly affects the performance and the running condition of the new energy automobile, so that the prediction of the battery life of the battery pack becomes a crucial link in the research of the new energy automobile.
The conventional method for calculating the Battery life of a Battery pack is usually based on a classic calculation formula of a vehicle Battery Management System (BMS), that is, six parameters, such as charge/discharge capacity of the Battery pack, Battery temperature, and voltage/current information of a Battery, are substituted into the classic calculation formula of the BMS to calculate the Battery pack life. However, because the region and temperature information (such as the south area or the north area, the plateau or the plain area, etc.) of the vehicle to which the battery pack belongs, the usage information of the vehicle, and the driving behavior information of the vehicle user have influence on the service life of the battery pack, for example, the service life of the battery pack is influenced by temperature differences in different regions, and the service life of the battery is also influenced by driving behaviors (such as pedal depth and charging frequency) of different users.
Therefore, how to accurately predict the battery life of the battery pack and further accurately know the operation condition of the vehicle becomes an urgent problem to be solved
Disclosure of Invention
In view of this, embodiments of the present disclosure provide a method and an apparatus for predicting a battery life of a battery pack, so as to solve the technical problem in the prior art that the battery life of the battery pack cannot be accurately predicted.
In order to solve the above problem, the technical solution provided by the embodiment of the present application is as follows:
in a first aspect, an embodiment of the present application provides a method for predicting a battery life of a battery pack, including:
acquiring battery use data of a target battery pack to be predicted;
inputting the battery use data into a pre-constructed battery life prediction model to obtain the probability density that the SOH of the target battery pack reaches a preset value;
and predicting the battery life of the target battery pack according to the probability density.
Optionally, the battery usage data includes a historical charging time of the target battery pack, battery related data of the target battery pack, user behavior data of a vehicle to which the target battery pack belongs, and a temperature control parameter and a current control parameter of a BMS of the vehicle to which the target battery pack belongs.
Optionally, constructing the battery life prediction model includes:
acquiring a first training parameter of the SOH of the battery pack at a first preset value;
Acquiring a second training parameter of the SOH of the battery pack at a second preset value;
and training an initial battery life prediction model by using the first training parameter and the second training parameter of the battery pack and the corresponding battery pack life label to generate the battery life prediction model.
Optionally, the initial battery life prediction model comprises a deep neural network DNN.
Optionally, the method further includes:
acquiring a service life verification parameter of the battery pack;
inputting the service life verification parameters of the battery pack into the battery life prediction model to obtain a battery life prediction result corresponding to the service life verification parameters of the battery pack;
and when the battery life prediction result corresponding to the battery pack life verification parameter is inconsistent with the battery life marking result corresponding to the battery pack life verification parameter, the battery pack life verification parameter is used as the training parameter of the battery pack again, and the battery life prediction model is updated.
Optionally, after predicting the battery life of the target battery, the method further includes:
when the predicted battery life of the target battery reaches a preset threshold value, adjusting the temperature control parameter and/or the current control parameter of the BMS of the vehicle to which the target battery pack belongs to prolong the battery life of the target battery pack
In a second aspect, the present application provides a battery life prediction apparatus for a battery pack, including:
the battery data acquisition unit is used for acquiring battery use data of a target battery pack to be predicted;
a probability density obtaining unit, configured to input the battery usage data to a battery life prediction model that is constructed in advance, and obtain a probability density at which the SOH of the target battery pack reaches a preset value;
and the battery life prediction unit is used for predicting the battery life of the target battery pack according to the probability density.
Optionally, the battery usage data includes a historical charging time of the target battery pack, battery related data of the target battery pack, user behavior data of a vehicle to which the target battery pack belongs, and a temperature control parameter and a current control parameter of a BMS of the vehicle to which the target battery pack belongs.
Optionally, the apparatus further comprises:
the first training parameter acquisition unit is used for acquiring a first training parameter of the SOH of the battery pack at a first preset value;
the second training parameter acquisition unit is used for acquiring a second training parameter of the SOH of the battery pack at a second preset value;
and the prediction model generation unit is used for training an initial battery life prediction model by using the first training parameter and the second training parameter of the battery pack and the corresponding battery pack life label to generate the battery life prediction model.
Optionally, the initial battery life prediction model comprises a deep neural network DNN.
Optionally, the apparatus further comprises:
a verification parameter acquisition unit for acquiring a life verification parameter of the battery pack;
the prediction result obtaining unit is used for inputting the service life verification parameters of the battery pack into the battery service life prediction model and obtaining a battery service life prediction result corresponding to the service life verification parameters of the battery pack;
and the prediction model updating unit is used for updating the battery life prediction model by taking the battery pack life verification parameters as the training parameters of the battery pack again when the battery life prediction result corresponding to the battery pack life verification parameters is inconsistent with the battery life marking result corresponding to the battery pack life verification parameters.
Optionally, the apparatus further comprises:
and the parameter adjusting unit is used for adjusting the temperature control parameter and/or the current control parameter of the BMS of the vehicle to which the target battery pack belongs so as to prolong the battery life of the target battery pack when the predicted battery life of the target battery reaches a preset threshold value.
An embodiment of the present application further provides a device for predicting a battery life of a battery pack, including: a processor, a memory, a system bus;
The processor and the memory are connected through the system bus;
the memory is used for storing one or more programs, and the one or more programs comprise instructions which, when executed by the processor, cause the processor to execute any one implementation of the battery life prediction method of the battery pack.
An embodiment of the present application further provides a computer-readable storage medium, where instructions are stored in the computer-readable storage medium, and when the instructions are executed on a terminal device, the terminal device is enabled to execute any implementation manner of the method for predicting the battery life of a battery pack.
According to the method and the device for predicting the battery life of the battery pack, the battery use data of the target battery pack to be predicted are obtained firstly, then the battery use data are used as input data and input into a pre-constructed battery life prediction model, so that the probability density that the SOH of the target battery pack reaches the preset value is output through the model, and the battery life of the target battery pack can be accurately predicted according to the probability density. Compared with the conventional method for calculating the battery life of the battery pack by using the classical calculation formula of the BMS, the method and the device fully consider the influence that the mutual influence between different use conditions of the vehicle in different time periods and the environment (such as the mutual influence factors of the environment temperature of the vehicle, the vehicle use time, the user driving behavior and the like) possibly causes on the vehicle-mounted battery pack in the actual operation process, so that the prediction accuracy of the battery life of the target battery pack can be effectively improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic flowchart of a method for predicting battery life of a battery pack according to an embodiment of the present disclosure;
fig. 2 is a schematic distribution diagram of charging time provided by an embodiment of the present application;
FIG. 3 is a schematic diagram of a distribution of initial charge amounts provided by an embodiment of the present application;
FIG. 4 is a schematic illustration of a depth profile of an accelerator pedal according to an embodiment of the present disclosure;
FIG. 5 is a schematic diagram of a distribution of probability densities provided by an embodiment of the present application;
fig. 6 is a schematic flowchart of constructing a battery life prediction model according to an embodiment of the present disclosure;
FIG. 7 is a schematic diagram of a process for constructing a first-stage and second-stage battery life prediction models according to an embodiment of the present disclosure;
fig. 8 is a schematic flowchart of a method for verifying a battery life prediction model according to an embodiment of the present disclosure;
Fig. 9 is a schematic composition diagram of a device for predicting battery life of a battery pack according to an embodiment of the present disclosure.
Detailed Description
In some battery pack life prediction methods, six parameters, such as charge/discharge capacity and battery temperature, of a battery pack are directly substituted into a classical calculation formula based on a vehicle-mounted BMS to calculate the battery life. However, this prediction method does not consider the interaction between various different usage conditions (such as charging habits of users and habits of pressing an accelerator pedal) and different environments (such as ambient temperature and humidity of the vehicle) of the vehicle in each time period during actual operation, which may affect the vehicle-mounted battery, so that the calculated battery life of the battery pack may be in error, thereby reducing the accuracy of predicting the battery life of the battery pack.
In order to solve the above-mentioned drawbacks, an embodiment Of the present application provides a method for predicting battery life Of a battery pack, where after a target battery pack to be predicted is obtained, battery usage data Of the target battery pack is obtained first, and then the battery usage data is input as input data to a battery life prediction model that is constructed in advance, so that a probability density that a State Of Health (SOH) Of the target battery pack reaches a preset value is output through the model, and then the battery life Of the target battery can be predicted accurately according to the probability density, and thus, in the embodiment Of the present application, only one battery life prediction model is needed, and based on each item Of battery usage data Of the target battery in each time period, the battery usage life Of the target battery pack can be predicted accurately, the prediction basis is more comprehensive, and influences that may be caused by mutual influences between different usage conditions Of the vehicle in each time period in actual operation and an environment where the vehicle is located are fully considered, therefore, the prediction accuracy of the service life of the target battery pack can be effectively improved.
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
First embodiment
Referring to fig. 1, a schematic flow chart of a method for predicting battery life of a battery pack provided in this embodiment is shown, where the method includes the following steps:
s101: and acquiring battery use data of the target battery pack to be predicted.
In this embodiment, a battery pack for which battery life prediction is required is defined as a target battery pack. Also, the present embodiment does not limit the battery type of the target battery pack, for example, the target battery pack may be a lithium ion battery pack, a nickel metal hydride battery pack, or the like.
Specifically, since the usage habits of users in different vehicles and the driving environment of the vehicle are different, the wear of the vehicle-mounted battery pack is different, that is, the service life of the vehicle-mounted battery pack is affected differently by the different usage conditions of the vehicle in different time periods and the mutual influence between the environment of the vehicle, so that in order to accurately predict the battery life of the target battery pack, it is first necessary to acquire the battery usage data of the target battery pack in each time period.
Among them, in an alternative implementation manner, the battery usage data may include a historical charging time of the target battery pack, battery-related data of the target battery pack, user behavior data of a vehicle to which the target battery pack belongs, and a temperature control parameter and a current control parameter of a BMS of the vehicle to which the target battery pack belongs.
In this implementation manner, the battery related data of the target battery pack refers to data related to characteristics of the target battery pack, such as voltage, current, and the like corresponding to the battery pack, and an ambient temperature where the target battery pack is located, and may further include distribution of charging time of the target battery at each time, as shown in fig. 2, for the target battery pack, a probability of each charging time period is different, for example, a probability of 11% corresponding to a charging time period of 11-20 minutes is different, and probabilities of other charging time periods are shown in fig. 2. Moreover, the battery related data of the target battery pack may further include distribution of initial charge amounts (nuclear power states of the target battery pack) of the target battery pack at each charging time point, as shown in fig. 3, for the target battery pack, the initial charge amounts of the battery packs are different, and corresponding charging probabilities are different, for example, when the initial charge amount is 21-30%, the probability of charging is 11.25%, and the charging probabilities corresponding to other initial charge amounts are shown in fig. 3, it can be understood that different charging times and different charging durations have different influences on the service life of the battery pack.
In this implementation manner, the user behavior data of the vehicle to which the target battery pack belongs refers to a series of driving behavior data corresponding to the user when the vehicle to which the target battery pack belongs is driven, such as a braking habit, a habit of stepping on an accelerator pedal, and the like of the user, as shown in fig. 4, which shows a distribution diagram of the depth of the accelerator pedal. It will be appreciated that different braking habits, different accelerator pedal depression depths will have different effects on the life of the battery pack.
Based on this, after the battery usage data corresponding to the target battery pack is acquired, the battery life of the target battery pack can be predicted through subsequent steps S102 to S103 by using the mutual influence between the battery usage data.
S102: and inputting the battery use data into a pre-constructed battery life prediction model to obtain the probability density that the SOH of the target battery pack reaches a preset value.
In this embodiment, after the battery usage data of the target battery pack to be predicted is obtained in step S101, the battery usage data may be further processed by using an existing or future data processing method, for example, a Principal Component Analysis (PCA) or a feature extraction method such as Word2vec, etc., to extract feature data capable of representing relevant contents of the target battery pack from the battery usage data, and the feature data is input into a pre-constructed battery life prediction model, so as to output a probability density corresponding to a preset SOH of the target battery pack through the model.
Note that, in the present embodiment, the battery life end point of the target battery pack is set when the SOH of the target battery pack reaches 80%. Correspondingly, the probability density corresponding to the target battery pack output by the battery life prediction model when the SOH of the target battery pack reaches the preset value refers to the probability density corresponding to the target battery pack when the SOH of the target battery pack reaches 80%, and the corresponding plane coordinates in the probability density distribution are the service mileage and the service life of the vehicle respectively, as shown in fig. 5, it can be seen from fig. 5 that the SOH of the corresponding target battery pack reaches 80% of the probability distribution condition when the vehicle to which the target battery pack belongs is in different service lives and different service mileage.
It can be understood that the battery life cut-off point of the target battery pack may be set to different values according to actual situations, that is, the battery life cut-off point of the target battery pack may be set when the SOH of the target battery pack reaches other preset values (e.g., 75%) other than 80%, which is not limited in this application. For convenience of description, the battery life end point of the target battery pack is set when the SOH of the target battery pack reaches 80%, and the preset value is processed in a similar manner, which is not described again.
It should be noted that, in order to implement step S102, a battery life prediction model needs to be constructed in advance, and the specific construction process can be referred to in the related description of the second embodiment.
S103: and predicting the battery life of the target battery pack according to the probability density.
In this embodiment, after the probability density that the SOH of the target battery pack reaches the preset value is obtained in step S102, the corresponding vehicle service life and the vehicle service mileage when the target battery pack reaches the battery life cutoff point can be further found from the probability density distribution map, so that the battery life of the target battery pack can be accurately predicted.
Specifically, after acquiring the probability density distribution map that the SOH of the target battery pack reaches the preset value, the vehicle service life and the vehicle service mileage corresponding to the time when the target battery pack reaches the battery life cutoff point may be acquired by: the first mode is to find out the service life and the service mileage of the vehicle corresponding to the highest position of the probability density in the probability density distribution diagram, and use the service life and the service mileage of the vehicle as the service life of the target battery pack when the target battery pack reaches the cut-off point of the battery life, so that the battery life of the target battery pack can be accurately predicted.
In the second mode, mathematical expectations can be respectively obtained for the numerical values of the two coordinate axes of the service life and the service mileage of the probability density distribution diagram, and the obtained service life expectation value and the obtained service mileage expectation value are respectively used as the corresponding vehicle service life and the corresponding vehicle service mileage when the target battery pack reaches the battery life cut-off point, so that the battery life of the target battery pack can be accurately predicted.
In one possible implementation manner of this embodiment, after the battery life of the target battery pack is predicted through step S103, when the predicted battery life of the target battery reaches a preset threshold, the temperature control parameter and/or the current control parameter of the BMS of the vehicle to which the target battery pack belongs are/is adjusted to prolong the battery life of the target battery pack.
In this implementation manner, after the battery life of the target battery pack is predicted through S103, it may be further determined whether the battery life reaches a preset threshold, if so, the battery life of the target battery pack may be prolonged by adjusting a temperature control parameter and/or a current control parameter of a BMS of a vehicle to which the target battery pack belongs, and if not, the battery life of the target battery pack may not be adjusted. The preset threshold refers to a critical value for distinguishing whether to adjust the temperature control parameter and/or the current control parameter of the BMS, and if the predicted battery life is less than the critical value, the temperature control parameter of the BMS needs to be adjusted in order to extend the battery life of the target battery pack.
Specifically, the BMS parameters which can be regulated and controlled at present only comprise the charging and discharging temperature and the charging and discharging current. Therefore, in order to extend the battery life of the target battery pack, it is necessary to adjust the temperature control parameter and/or the current control parameter of the BMS. When the parameters are adjusted, the energy consumption of the target vehicle during charging, the energy consumption during discharging, the driving range, the charging time, the charging electric quantity, the driving experience and the like are inevitably affected. Therefore, in order not to affect the usage habits and experiences of the user, it is necessary to monitor and balance the influence of the adjustment parameters while adjusting the temperature control parameters and/or the current control parameters of the BMS to optimize the battery life (i.e., to extend the service life and the service mileage of the vehicle to which the target battery pack belongs).
For example, the following steps are carried out: according to the probability density distribution output by the model as shown in fig. 5, assuming that when the service life of the vehicle to which the target battery pack belongs is predicted to be only 1 year, in order to extend the service life of the target battery pack, that is, in order to shift the value of the highest point position of the probability density in fig. 5 "backward" to make the corresponding service life and service mileage larger, or in order to increase the service life expected value and service mileage expected value obtained by respectively obtaining the mathematical expectation values for the values of the two coordinate axes of the service life and service mileage of the probability density distribution map, the charging and discharging temperature and/or the charging and discharging current of the BMS of the vehicle to which the target battery pack belongs may be adjusted so as to output a diagram showing that the highest value distribution of the probability density is further backward or obtain a higher service life expected value and service mileage by executing the above steps S101 to S102 using the battery life prediction model, that is, a longer service life and/or a longer use range of the vehicle to which the target battery pack belongs are predicted, that is, the battery life of the target battery pack is extended.
It should be noted that, when selecting the temperature control parameter and/or the current control parameter of the BMS of the vehicle to which the target battery pack belongs, an existing or future optimal value selection calculation method may be adopted to calculate the optimal solution of the corresponding temperature control parameter and/or current control parameter, for example, a gradient descent method may be used to obtain the optimal value of the temperature control parameter and/or current control parameter in combination with the driving behavior habit of the user, and the optimal value is used as an adjustment value to prolong the battery life of the target battery.
Therefore, the battery life of the target battery pack is accurately predicted through the embodiment of the application, so that a user can fully know the factors influencing the battery pack life of the target vehicle, and the quality of the battery pack core of the target battery pack can be accurately evaluated according to the prediction result.
In summary, according to the method for predicting the battery life of the battery pack provided in this embodiment, after the target battery pack to be predicted is obtained, the battery usage data of the target battery pack may be obtained first, and then the battery usage data is input to the battery life prediction model which is constructed in advance as input data, so that the probability density that the SOH of the target battery pack reaches the preset value is output through the model, and the battery life of the target battery pack may be accurately predicted according to the probability density. Compared with the conventional method for calculating the battery life of the battery pack by using the classical calculation formula of the BMS, the method for predicting the battery life of the battery pack only needs one battery life prediction model, can accurately predict the battery life of the target battery pack based on various battery use data of the target battery in various time periods, has more comprehensive prediction basis, and fully considers the influence possibly caused by the mutual influence between different use conditions of the vehicle in various time periods and the environment where the vehicle is located in the actual operation process on the vehicle-mounted battery pack, so that the accuracy rate of predicting the battery life of the target battery pack can be effectively improved.
Second embodiment
The present embodiment will describe a specific construction process of the battery life prediction model mentioned in the first embodiment. The battery life of the target battery pack can be accurately and quickly predicted by using the pre-constructed battery life prediction model.
Referring to fig. 6, it shows a schematic flowchart of a process for constructing a battery life prediction model according to the present embodiment, where the process includes the following steps:
s601: a first training parameter of the SOH of the battery pack at a first preset value is obtained.
In the present embodiment, in order to construct the battery life prediction model, a large amount of preparation work needs to be performed in advance, and first, it is necessary to collect battery usage data of the battery pack as training parameters. It should be noted that, because the existing real data is limited, in order to improve the prediction accuracy of the model, the training parameters for which the SOH reaches 92% (defined as the first preset value) are the real battery pack usage data (such as battery related data and/or user behavior data), and the training parameters corresponding to the SOH reaches 80% (defined as the second preset value) are trained by using laboratory data, that is, the model training may be performed by dividing the model training into two stages, as shown in fig. 7, the battery usage data for which the SOH of the battery pack is obtained at the first preset value (92%) may be first used as the first training parameters, and the collected first training parameters of each battery pack are respectively used as sample parameter data to train the battery life prediction model in the first stage.
S602: and acquiring a second training parameter of the SOH of the battery pack at a second preset value.
In order to construct the battery life prediction model, it is further required to acquire battery usage data (laboratory data) of the battery packs with the SOH at a second preset value (i.e., 80%) as second training parameters, and use the collected second training parameters of each battery pack as sample parameter data respectively, so as to train the battery life prediction model at the second stage.
S603: and training the initial battery life prediction model by using the first training parameter and the second training parameter of the battery pack and the corresponding battery pack life label to generate a battery life prediction model.
In this embodiment, as shown in fig. 7, after the first training parameters (battery related data and user behavior data) of the battery pack are obtained in step S601, the first training parameters may be further processed by using an existing or future data processing method to extract feature data capable of representing related contents of the battery pack, and further, the initial battery life prediction model may be trained according to the feature data and a real battery life labeling result corresponding to the first training parameters, so as to generate the first-stage battery life prediction model.
In an optional implementation manner, the initial battery life prediction model may include a Deep Neural Network (DNN).
Then, a set of sample parameter data may be sequentially extracted from the model training data, and multiple rounds of model training may be performed until the training end condition is satisfied, at which time, the battery life prediction model of the first stage is generated.
Specifically, during the current round of training, the battery usage data of the target battery pack in the first embodiment may be replaced by the sample parameter data extracted in the current round, the probability density that the SOH of the battery pack represented by the sample parameter data reaches 92% may be predicted according to the execution process in the first embodiment through the current initial battery life prediction model, so as to predict the battery life of the battery pack, and the predicted battery life is compared with the corresponding artificially labeled real battery life labeling result, and the model parameter is updated according to the difference between the two results until a preset condition is met, for example, the difference change amplitude is small, the update of the model parameter is stopped, the training of the first-stage battery life prediction model is completed, and a trained first-stage battery life prediction model is generated.
Next, as shown in fig. 7, after the second training parameters (laboratory data) of the battery pack are acquired in step S602, a battery life prediction model in the second stage, that is, a final battery life prediction model, may be generated by training based on the battery life prediction model in the first stage by using a laboratory modeling method. The specific calculation formula is as follows:
SOH＝1-Qloss (1)
Qloss＝Qcycleloss+Qcalenderloss (2)
wherein QlossRepresenting the estimated current capacity loss of the battery pack; qcyclelossRepresenting the capacity loss caused by circulation, wherein the capacity loss caused by circulation considers the influences of temperature, historical charge capacity, charge-discharge rate and discharge depth; qcalenderlossAnd the capacity loss caused by placing is expressed, and the influence of the temperature, the nuclear power state of the battery pack and the placing time is considered.
QcyclelossThe specific calculation formula of (2) is as follows:
the values of the battery pack cells of different types can be different and can be obtained through experiments; g1(DOD) represents the relationship of the loss of cyclic capacity with the Depth of discharge (DOD); g2(Crate) denotes the loss of circulating capacity with Crate(charging rate); t represents a temperature; ah represents the historical charge capacity.
On the basis, the circulation capacity loss caused by one time of charging 1Ah electric quantity can be calculated, and the specific calculation formula is as follows:
It should be noted that, when calculating the placement capacity loss at present, only the capacity loss caused by placing the battery pack core at 25 ℃ and 50% SOC is usually considered, and after obtaining the battery factory date, the BMS may obtain the number of days of placement by comparing with the current real-time date, and then may obtain the capacity loss caused by placement by using the existing experimental data (25 ℃, 50% SOC) in a table look-up manner.
However, in this embodiment, in order to improve the model accuracy, the capacity loss Q caused by the placement of the calculation is increasedcalenderlossWhen is added withModification of SOC and temperature so that QcalenderlossThe specific calculation formula is as follows
Wherein D represents the number of days of standing; SOC is SOC, f of battery pack core after starting up1(SOC) represents capacity loss due to placement versus SOC; and T represents the temperature of the battery pack core after the battery pack is started.
On the basis, capacity loss caused by one-time placement can be calculated every day of placement, and the specific calculation formula is as follows:
based on the above, by executing the above process, the trained battery life prediction model in the first stage is trained for multiple rounds, and after the preset conditions are met, the updating of the model parameters is stopped, the training of the battery life prediction model in the second stage is completed, and a trained battery life prediction model in the second stage is generated to be used as a final battery life prediction model.
Through the embodiment, the first training parameter and the second training parameter can be used for training to generate the battery life prediction model, and further, the generated battery life prediction model can be verified by using the life verification parameter of the battery pack.
The following describes a method for verifying a battery life prediction model according to an embodiment of the present application with reference to the accompanying drawings.
Referring to fig. 8, which shows a flowchart of a battery life prediction model verification method provided in an embodiment of the present application, as shown in fig. 8, the method includes:
s801: and acquiring the service life verification parameters of the battery pack.
In this embodiment, in order to implement the verification of the battery life prediction model, first, life verification parameters of the battery pack need to be obtained, where the life verification parameters of the battery pack refer to various items of usage data of the battery that can be used for performing the verification of the battery life prediction model, such as voltage, current, temperature, usage time, ambient temperature, behavior data of the user, and the like of the battery pack, and after the life verification parameters of the battery pack are obtained, the step S802 may be continuously performed.
S802: and inputting the service life verification parameters of the battery pack into the battery life prediction model to obtain a battery life prediction result corresponding to the service life verification parameters of the battery pack.
In this embodiment, after the life verification parameters of the battery pack are obtained in step S801, after the feature data capable of representing the relevant content of the battery pack is extracted, the feature data may be input to the trained battery life prediction model, and according to the probability density distribution diagram output by the model, the prediction result of the battery life corresponding to the life verification parameters of the battery pack is obtained, so that step S803 may be continuously executed.
S803: and when the battery life prediction result corresponding to the battery pack life verification parameter is inconsistent with the battery life marking result corresponding to the battery pack life verification parameter, the battery pack life verification parameter is used as the training parameter of the battery pack again, and the battery life prediction model is updated.
In this embodiment, after the battery life of the battery pack is predicted in step S802, when the prediction result is inconsistent with the manual labeling result corresponding to the battery pack life verification parameter, the battery pack life verification parameter may be used as the model training parameter again to update the battery life prediction model.
Through the embodiment, the battery pack service life verification parameters can be utilized to effectively verify the battery service life prediction model, and when the battery service life prediction result corresponding to the battery pack service life verification parameters is inconsistent with the manual marking result corresponding to the battery pack service life verification parameters, the battery service life prediction model can be adjusted and updated in time, so that the prediction precision and accuracy of the prediction model can be improved.
In summary, the battery life prediction model trained by the embodiment can be used to predict the battery life of the target battery pack by using the battery usage data representing the relevant content of the target battery pack, and in the prediction process, the influence that the mutual influence between different usage conditions of the vehicle in different time periods and the environment where the vehicle is located may cause on the vehicle-mounted battery pack is fully considered, so that the prediction accuracy of the battery life of the target battery pack can be effectively improved.
Third embodiment
In this embodiment, a battery life prediction apparatus for a battery pack will be described, and please refer to the above method embodiments for related contents.
Referring to fig. 9, a schematic composition diagram of a battery life predicting device for a battery pack provided in this embodiment is shown, where the device includes:
a battery data acquiring unit 901 configured to acquire battery usage data of a target battery pack to be predicted;
a probability density obtaining unit 902, configured to input the battery usage data into a pre-constructed battery life prediction model, so as to obtain a probability density that the SOH of the target battery pack reaches a preset value;
and a battery life prediction unit 903, configured to predict the battery life of the target battery pack according to the probability density.
In one implementation manner of this embodiment, the battery usage data includes a historical charging time of the target battery pack, battery-related data of the target battery pack, user behavior data of a vehicle to which the target battery pack belongs, and a temperature control parameter and a current control parameter of a BMS of the vehicle to which the target battery pack belongs.
In an implementation manner of this embodiment, the apparatus further includes:
the first training parameter acquisition unit is used for acquiring a first training parameter of the SOH of the battery pack at a first preset value;
the second training parameter acquisition unit is used for acquiring a second training parameter of the SOH of the battery pack at a second preset value;
and the prediction model generation unit is used for training an initial battery life prediction model by using the first training parameter and the second training parameter of the battery pack and the corresponding battery pack life label to generate the battery life prediction model.
In one implementation of this embodiment, the initial battery life prediction model includes a deep neural network DNN.
In an implementation manner of this embodiment, the apparatus further includes:
the verification parameter acquisition unit is used for acquiring the service life verification parameters of the battery pack;
The prediction result obtaining unit is used for inputting the service life verification parameters of the battery pack into the battery service life prediction model and obtaining a battery service life prediction result corresponding to the service life verification parameters of the battery pack;
and the prediction model updating unit is used for updating the battery life prediction model by taking the battery pack life verification parameters as the training parameters of the battery pack again when the battery life prediction result corresponding to the battery pack life verification parameters is inconsistent with the battery life marking result corresponding to the battery pack life verification parameters.
In an implementation manner of this embodiment, the apparatus further includes:
and the parameter adjusting unit is used for adjusting the temperature control parameter and/or the current control parameter of the BMS of the vehicle to which the target battery pack belongs when the predicted battery life of the target battery reaches a preset threshold value, so as to prolong the battery life of the target battery pack.
In summary, after the target battery pack to be predicted is obtained, the battery usage data of the target battery pack may be obtained first, and then the battery usage data is input to the battery life prediction model that is constructed in advance as input data, so that the probability density that the SOH of the target battery pack reaches the preset value is output through the model, and the battery life of the target battery pack may be accurately predicted according to the probability density. Compared with the conventional method for calculating the battery life of the battery pack by using the classical calculation formula of the BMS, the method has the advantages that only one battery life prediction model is needed, the battery life of the target battery pack can be accurately predicted based on various battery use data of the target battery in various time periods, the prediction basis is more comprehensive, the influence of the different use conditions of the vehicle in various time periods in actual operation and the influence of the mutual influence between the environments of the vehicle in various time periods on the vehicle-mounted battery pack can be fully considered, and therefore the prediction accuracy of the battery life of the target battery pack can be effectively improved.
Further, an embodiment of the present application also provides a battery life prediction device for a battery pack, including: a processor, a memory, a system bus;
the processor and the memory are connected through the system bus;
the memory is used to store one or more programs, the one or more programs including instructions, which when executed by the processor, cause the processor to perform any of the above-described battery life prediction methods for a battery pack.
Further, an embodiment of the present application also provides a computer-readable storage medium, where instructions are stored in the computer-readable storage medium, and when the instructions are run on a terminal device, the instructions cause the terminal device to execute any implementation method of the above battery life prediction method for a battery pack.
As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that all or part of the steps in the above embodiment methods can be implemented by software plus a necessary general hardware platform. Based on such understanding, the technical solution of the present application may be essentially or partially implemented in the form of a software product, which may be stored in a storage medium, such as a ROM/RAM, a magnetic disk, an optical disk, etc., and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network communication device such as a media gateway, etc.) to execute the method according to the embodiments or some parts of the embodiments of the present application.
It should be noted that, in the present specification, the embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments may be referred to each other. The device disclosed in the embodiment corresponds to the method disclosed in the embodiment, so that the description is simple, and the relevant points can be referred to the description of the method part.
It is further noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A method for predicting battery life of a battery pack, comprising:
acquiring battery use data of a target battery pack to be predicted;
inputting the battery use data into a pre-constructed battery life prediction model to obtain the probability density that the SOH of the target battery pack reaches a preset value;
predicting the battery life of the target battery pack according to the probability density;
the battery usage data includes a historical charging time of the target battery pack, battery-related data of the target battery pack, user behavior data of a vehicle to which the target battery pack belongs, and a temperature control parameter and a current control parameter of a BMS of the vehicle to which the target battery pack belongs;
Wherein the battery-related data of the target battery pack includes: the ambient temperature of the target battery pack and the charging time distribution condition of the target battery pack at each time;
the user behavior data of the vehicle to which the target battery pack belongs includes: driving behavior data corresponding to a user when the user drives a vehicle to which the target battery pack belongs;
constructing the battery life prediction model, training an initial battery life prediction model by using the first training parameter and the second training parameter of the battery pack and the corresponding battery pack life label, and generating the battery life prediction model, wherein the method comprises the following steps:
acquiring a first training parameter of the SOH of the battery pack at a first preset value, wherein the first training parameter is as follows: processing the first training parameter by using a data processing method to extract characteristic data capable of representing the relevant content of the battery pack from the battery-related data and the user behavior data, and training an initial battery life prediction model according to the characteristic data and a real battery life marking result corresponding to the first training parameter to further generate a first-stage battery life prediction model;
acquiring a second training parameter of the SOH of the battery pack at a second preset value, wherein the second training parameter is laboratory data, and training and generating a second-stage battery life prediction model on the basis of the first-stage life prediction model by using a laboratory modeling method;
The calculation formula is as follows:
SOH＝1-Qloss
Qloss＝Qcycleloss+Qcalenderloss
wherein Q islossRepresenting the estimated current capacity loss of the battery pack; qcyclelossRepresenting the capacity loss caused by circulation, wherein the capacity loss caused by circulation considers the influences of temperature, historical charge capacity, charge-discharge rate and discharge depth; qcalenderlossIndicating capacity loss due to placement;
Qcyclelossthe specific calculation formula of (2) is as follows:
the battery pack core is obtained through experiments, wherein A, K and z are coefficients, and values of battery pack cores of different types can be different; g1(DOD) represents the cyclic capacity loss versus depth of discharge; g2(Crate) Represents the loss of cyclic capacity and CrateThe relationship of (1); t represents a temperature; ah represents the historical charge capacity.
2. The method of claim 1, wherein the initial battery life prediction model comprises a Deep Neural Network (DNN).
3. The method according to any one of claims 1 to 2, further comprising:
acquiring a service life verification parameter of the battery pack;
inputting the service life verification parameters of the battery pack into the battery life prediction model to obtain a battery life prediction result corresponding to the service life verification parameters of the battery pack;
and when the battery life prediction result corresponding to the battery pack life verification parameter is inconsistent with the battery life marking result corresponding to the battery pack life verification parameter, the battery pack life verification parameter is used as the training parameter of the battery pack again, and the battery life prediction model is updated.
4. The method of claim 1, wherein after predicting the battery life of the target battery, further comprising:
and when the predicted battery life of the target battery reaches a preset threshold value, adjusting the temperature control parameter and/or the current control parameter of the BMS of the vehicle to which the target battery pack belongs so as to prolong the battery life of the target battery pack.
5. A battery life prediction apparatus for a battery pack, comprising:
the battery data acquisition unit is used for acquiring battery use data of a target battery pack to be predicted;
a probability density obtaining unit, configured to input the battery usage data to a battery life prediction model that is constructed in advance, and obtain a probability density at which the SOH of the target battery pack reaches a preset value;
a battery life prediction unit for predicting the battery life of the target battery pack according to the probability density;
the battery usage data includes a historical charging time of the target battery pack, battery-related data of the target battery pack, user behavior data of a vehicle to which the target battery pack belongs, and a temperature control parameter and a current control parameter of a BMS of the vehicle to which the target battery pack belongs;
Wherein the battery-related data of the target battery pack includes: the ambient temperature of the target battery pack and the charging time distribution condition of the target battery pack at each time;
the user behavior data of the vehicle to which the target battery pack belongs includes: driving behavior data corresponding to a user when the user drives a vehicle to which the target battery pack belongs;
constructing the battery life prediction model, training an initial battery life prediction model by using the first training parameter and the second training parameter of the battery pack and the corresponding battery pack life label, and generating the battery life prediction model, wherein the method comprises the following steps:
the first training parameter obtaining unit is used for obtaining a first training parameter of the SOH of the battery pack at a first preset value, and the first training parameter is as follows: processing the first training parameter by using a data processing method to extract characteristic data capable of representing the relevant content of the battery pack from the battery-related data and the user behavior data, and training an initial battery life prediction model according to the characteristic data and a real battery life marking result corresponding to the first training parameter to further generate a first-stage battery life prediction model;
The second training parameter acquisition unit is used for acquiring a second training parameter of the SOH of the battery pack at a second preset value, the second training parameter is laboratory data, and a laboratory modeling method is utilized to train and generate a second-stage battery life prediction model on the basis of the first-stage life prediction model;
a prediction model generation unit;
the calculation formula is as follows:
SOH＝1-Qloss
Qloss＝Qcycleloss+Qcalenderloss
wherein Q islossRepresenting the estimated current capacity loss of the battery pack; qcyclelossRepresenting the capacity loss caused by circulation, wherein the capacity loss caused by circulation considers the influences of temperature, historical charge capacity, charge-discharge rate and discharge depth; qcalenderlossIndicating capacity loss due to placement;
Qcyclelossthe specific calculation formula of (2) is as follows:
the battery pack core is obtained through experiments, wherein A, K and z are coefficients, and values of battery pack cores of different types can be different; g1(DOD) represents the cyclic capacity loss versus depth of discharge; g2(Crate) Represents the loss of cyclic capacity and CrateThe relationship of (1); t represents a temperature; ah represents the historical charge capacity.
6. The apparatus of claim 5, wherein the initial battery life prediction model comprises a Deep Neural Network (DNN).
7. The apparatus of any of claims 5 to 6, further comprising:
A verification parameter acquisition unit for acquiring a life verification parameter of the battery pack;
the prediction result obtaining unit is used for inputting the service life verification parameters of the battery pack into the battery service life prediction model and obtaining a battery service life prediction result corresponding to the service life verification parameters of the battery pack;
and the prediction model updating unit is used for updating the battery life prediction model by taking the battery pack life verification parameters as the training parameters of the battery pack again when the battery life prediction result corresponding to the battery pack life verification parameters is inconsistent with the battery life marking result corresponding to the battery pack life verification parameters.
8. The apparatus of claim 5, further comprising:
and the parameter adjusting unit is used for adjusting the temperature control parameter and/or the current control parameter of the BMS of the vehicle to which the target battery pack belongs so as to prolong the battery life of the target battery pack when the predicted battery life of the target battery reaches a preset threshold value.
9. A battery-life predicting apparatus of a battery pack, comprising: a processor, a memory, a system bus;
the processor and the memory are connected through the system bus;
The memory is to store one or more programs, the one or more programs comprising instructions, which when executed by the processor, cause the processor to perform the method of any of claims 1-4.
10. A computer-readable storage medium having stored therein instructions that, when executed on a terminal device, cause the terminal device to perform the method of any one of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910935361.8A CN110658460B (en) | 2019-09-29 | 2019-09-29 | Battery life prediction method and device for battery pack |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910935361.8A CN110658460B (en) | 2019-09-29 | 2019-09-29 | Battery life prediction method and device for battery pack |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110658460A CN110658460A (en) | 2020-01-07 |
| CN110658460B true CN110658460B (en) | 2022-06-03 |
Family
ID=69038432
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910935361.8A Active CN110658460B (en) | 2019-09-29 | 2019-09-29 | Battery life prediction method and device for battery pack |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110658460B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11740290B2 (en) | 2020-01-14 | 2023-08-29 | Battelle Energy Alliance, Llc | Energy storage cell qualification and related systems, methods, and devices |
| CN112485693B (en) * | 2020-11-19 | 2022-09-27 | 上海电力大学 | Battery health state rapid evaluation method based on temperature probability density function |
| CN112668852A (en) * | 2020-12-22 | 2021-04-16 | 东软睿驰汽车技术（沈阳）有限公司 | Method and device for evaluating influence of user usage behavior on battery pack aging |
| CN113219347A (en) * | 2021-04-27 | 2021-08-06 | 东软睿驰汽车技术（沈阳）有限公司 | Battery parameter measuring method and device |
| CN114217237A (en) * | 2021-11-05 | 2022-03-22 | 东软睿驰汽车技术（沈阳）有限公司 | Battery health state determination method and device based on storage endurance and electronic equipment |
| CN114062954B (en) * | 2021-11-09 | 2022-11-08 | 湖南省驰普新能源科技有限公司 | Battery pack service life detection charging and discharging system and method |
| CN114295998B (en) * | 2021-12-28 | 2024-07-09 | 东软睿驰汽车技术（沈阳）有限公司 | Method, device, equipment and storage medium for predicting service life of power battery |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100486033C (en) * | 2005-08-08 | 2009-05-06 | 丰田自动车株式会社 | Powertrain battery life predicting and warning apparatuses |
| JP5155740B2 (en) * | 2008-05-30 | 2013-03-06 | 株式会社東芝 | MONITORING CONDITION DETERMINING DEVICE, MONITORING CONDITION DETERMINING METHOD, AND MONITORING DIAGNOSIS DEVICE |
| CN104881001A (en) * | 2014-04-25 | 2015-09-02 | 安徽贵博新能科技有限公司 | Energy storage battery management system based on deep learning network |
| CN105425167A (en) * | 2015-12-30 | 2016-03-23 | 广东顺德中山大学卡内基梅隆大学国际联合研究院 | Battery revaluation and battery insurance evaluation system based on driving habit and battery use data |
| CN107045103B (en) * | 2016-11-29 | 2020-02-04 | 北京长城华冠汽车科技股份有限公司 | Device and method for testing service life of power battery of electric automobile |
| US11131713B2 (en) * | 2018-02-21 | 2021-09-28 | Nec Corporation | Deep learning approach for battery aging model |
| CN108680861B (en) * | 2018-03-05 | 2021-01-01 | 北京航空航天大学 | Method and device for constructing lithium battery residual cycle life prediction model |
| CN109934294A (en) * | 2019-03-18 | 2019-06-25 | 常伟 | A method of batteries of electric automobile SOH prediction is carried out based on big data machine learning |
| CN110222426A (en) * | 2019-06-06 | 2019-09-10 | 南京航空航天大学 | Aircraft battery method for predicting residual useful life under discontinuous operating mode |
-
2019
- 2019-09-29 CN CN201910935361.8A patent/CN110658460B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN110658460A (en) | 2020-01-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110658460B (en) | Battery life prediction method and device for battery pack | |
| CN112666464B (en) | Battery health state prediction method, device, electronic equipment and readable storage medium | |
| Zhang et al. | Battery modelling methods for electric vehicles-A review | |
| CN110598300A (en) | Battery SOH prediction method and device | |
| CN109100655B (en) | Data processing method and device for power battery | |
| CN107132490B (en) | Method for estimating state of charge of lithium battery pack | |
| CN110568359A (en) | lithium battery residual life prediction method | |
| WO2015041093A1 (en) | Device and method for evaluating performance of storage cell | |
| CN112622693A (en) | Battery management method and device and vehicle | |
| KR20220073829A (en) | Battery Performance Prediction | |
| WO2022144542A1 (en) | Method for predicting condition parameter degradation of a cell | |
| JP2023139227A (en) | Battery health state prediction method, device, and electronic instrument and readable storage medium | |
| CN113219357A (en) | Battery pack health state calculation method and system and electronic equipment | |
| Shi et al. | Electric vehicle battery remaining charging time estimation considering charging accuracy and charging profile prediction | |
| US20230305073A1 (en) | Method and apparatus for providing a predicted aging state of a device battery based on a predicted usage pattern | |
| CN110674569A (en) | Charging remaining time estimation method and system based on decision tree | |
| CN115700717A (en) | Power distribution analysis method based on electric automobile power consumption demand | |
| CN115600728A (en) | Annual carbon emission estimation method and device for power battery | |
| CN109840353B (en) | Lithium ion battery two-factor inconsistency prediction method and device | |
| CN109800477B (en) | Lithium ion battery three-factor inconsistency prediction method and device | |
| CN108845267B (en) | Data processing method and device for power battery | |
| CN113119796B (en) | Electric vehicle residual charging time prediction method and system based on cloud sparse charging data | |
| CN114114051A (en) | Method and device for determining battery aging value and electronic equipment | |
| El Ouazzani et al. | MSCC-DRL: Multi-Stage constant current based on deep reinforcement learning for fast charging of lithium ion battery | |
| CN106154170B (en) | The evaluation method and system of battery remaining power |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |