CN115291111A - Training method of battery standing time prediction model and standing time prediction method - Google Patents
Training method of battery standing time prediction model and standing time prediction method Download PDFInfo
- Publication number
- CN115291111A CN115291111A CN202210927520.1A CN202210927520A CN115291111A CN 115291111 A CN115291111 A CN 115291111A CN 202210927520 A CN202210927520 A CN 202210927520A CN 115291111 A CN115291111 A CN 115291111A
- Authority
- CN
- China
- Prior art keywords
- battery
- data
- capacity
- sample
- standing time
- 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.)
- Granted
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]
- G01R31/385—Arrangements for measuring battery or accumulator variables
Abstract
The invention discloses a training method of a battery standing time prediction model and a standing time prediction method. The method comprises the steps of obtaining sample batteries for model training, and determining battery type data corresponding to each sample battery; determining battery capacity data respectively corresponding to each sample battery in a capacity test process; training the standing time prediction model based on battery capacity data and battery type data respectively corresponding to the sample batteries to obtain a trained standing time prediction model; the standing time prediction model is used for predicting the standing time of the battery in the standing stage in the capacity test process. The technical scheme disclosed by the invention solves the problem that the static time obtained by estimation in the prior art influences the efficiency and accuracy of the test, and realizes the purpose of providing accurate static time, thereby improving the accuracy of the test result.
Description
Technical Field
The invention relates to the technical field of battery testing, in particular to a training method of a battery standing time prediction model and a standing time prediction method.
Background
The battery management system is one of the core components of the vehicle, and in order to make the vehicle normally operate, the battery must be in a normal operation state, that is, the battery capacity needs to be tested, so as to determine the operation state of the battery。
When the capacity of the battery is tested, the battery is discharged until the cut-off voltage is finished after the battery is fully charged and then is kept still for a period of time, and the capacity of the battery is calculated through a formula. Generally, the standing time refers to the time of not less than 30 minutes or not more than 60 minutes in the national standard, but because the capacity test time is longer, the standing time directly influences the test time and the test effect, namely, under the same charging system, the discharge capacity test is carried out after standing for 10 minutes and standing for 1 hour, and the result also has a difference of 2-5%, which is specifically determined by the self-discharge performance of the battery.
The current standing time is determined mainly by approximately estimating a time based on experience of the test in combination with the material, kind, and the like of the battery. The estimated standing time based on the above manner affects the efficiency and accuracy of the test, thereby reducing the reliability of the test result.
Disclosure of Invention
The invention provides a training method of a battery standing time prediction model and a standing time prediction method, which are used for solving the problem that the efficiency and the accuracy of a test are influenced by the estimated standing time in the prior art, and realizing the purpose of providing accurate standing time, thereby improving the accuracy of a test result.
In a first aspect, an embodiment of the present invention provides a method for training a battery standing time prediction model, where the method includes:
obtaining sample batteries for model training, and determining battery type data corresponding to each sample battery;
determining battery capacity data respectively corresponding to each sample battery in a capacity test process;
training the standing time prediction model based on battery capacity data and battery type data respectively corresponding to the sample batteries to obtain a trained standing time prediction model; the standing time prediction model is used for predicting the standing time of the battery in the standing stage in the capacity test process.
Optionally, the determining battery capacity data respectively corresponding to each sample battery in the capacity testing process includes:
acquiring current data and voltage data of each sample battery in a capacity test process;
and determining battery capacity data corresponding to the sample batteries respectively based on the current data and the voltage data.
Optionally, the obtaining current data and voltage data of each sample battery in the capacity test process includes:
for any sample battery, reading system current data and system voltage data of the current sample battery based on a preset battery management system;
acquiring current data and voltage data of the current sample battery based on a preset data acquisition device;
and acquiring the test current data and the test voltage data of the current sample battery based on the charge and discharge equipment in the capacity test process.
Optionally, the determining, based on the current data and the voltage data, battery capacity data corresponding to each sample battery includes:
for any sample battery, determining system battery capacity data of the current sample battery based on the system current data and the system voltage data;
determining the collected battery capacity data of the current sample battery based on the collected current data and the collected voltage data;
determining test battery capacity data of the current sample battery based on the test current data and the test voltage data;
and determining the battery capacity data of the current sample battery based on the system battery capacity data, the acquired battery capacity data and the test battery capacity data.
Optionally, the battery capacity data of each sample battery in the capacity testing process includes charging battery capacity data corresponding to a charging stage and standing battery capacity data corresponding to a standing stage;
correspondingly, the training of the standing time prediction model based on the battery capacity data and the battery type data respectively corresponding to each sample battery to obtain a trained standing time prediction model includes:
for any sample battery, determining the rechargeable battery capacity data and the static battery capacity data corresponding to the battery type data of the battery sample based on a preset battery corresponding relation;
and taking the battery type data, the rechargeable battery capacity data and the static battery capacity data as sample training data of the current sample battery, and training the static time prediction model to obtain a trained static time prediction model.
In a second aspect, an embodiment of the present invention further provides a method for predicting battery standing time, where the method includes:
acquiring a target battery and determining battery type data of the target battery;
determining the corresponding rechargeable battery capacity data of the target battery in the charging stage in the capacity testing process;
inputting the capacity data of the rechargeable battery and the type data of the battery into a pre-trained battery standing time prediction model to obtain the standing time of the target battery in a standing stage in the capacity testing process; the battery standing time prediction model is obtained by training based on the training method of the battery standing time prediction model in any embodiment.
In a third aspect, an embodiment of the present invention further provides a training device for a battery resting time prediction model, where the training device includes:
the system comprises a sample battery acquisition module, a model training module and a control module, wherein the sample battery acquisition module is used for acquiring sample batteries used for model training and determining battery type data corresponding to each sample battery;
the battery capacity data acquisition module is used for determining battery capacity data corresponding to each sample battery in the capacity test process;
the model training module is used for training the standing time prediction model based on battery capacity data and battery type data which respectively correspond to the sample batteries to obtain a trained standing time prediction model; the standing time prediction model is used for predicting the standing time of the battery in the standing stage in the capacity test process.
In a fourth aspect, an embodiment of the present invention further provides a device for predicting a battery standing time, where the device includes:
the system comprises a rechargeable battery capacity data acquisition module, a capacity test module and a capacity test module, wherein the rechargeable battery capacity data acquisition module is used for acquiring rechargeable battery capacity data corresponding to a target battery in a charging stage in a capacity test process;
a standing time obtaining module, configured to input the capacity data of the rechargeable battery into a pre-trained battery standing time prediction model, so as to obtain a standing time of the target battery in a standing stage in a capacity testing process; the battery standing time prediction model is obtained by training based on the training method of the battery standing time prediction model in any embodiment.
In a fifth aspect, an embodiment of the present invention further provides an electronic device, including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to enable the at least one processor to perform a method of training a battery rest time prediction model according to any of the embodiments of the present invention, and/or a method of predicting a battery rest time according to any of the embodiments.
In a sixth aspect, the present invention further provides a computer-readable storage medium, where computer instructions are stored, and the computer instructions are configured to, when executed by a processor, implement a training method for a battery standing time prediction model according to any embodiment of the present invention, and/or a battery standing time prediction method according to any embodiment.
The technical scheme of the embodiment of the invention specifically comprises the following steps: obtaining sample batteries for model training, and determining battery type data corresponding to each sample battery; determining battery capacity data respectively corresponding to each sample battery in the capacity testing process; training the standing time prediction model based on battery capacity data and battery type data respectively corresponding to each sample battery to obtain a trained standing time prediction model; the standing time prediction model is used for predicting the standing time of the battery in the standing stage in the capacity test process. According to the technical scheme, the battery standing time prediction model is trained by obtaining the type data of the sample battery and the battery capacity data in the capacity testing process, so that the trained battery standing time prediction model is obtained, the problem that the efficiency and the accuracy of the test are affected by the standing time obtained by estimation in the prior art is solved, the accurate standing time is provided, and the accuracy of the test result is improved.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present invention, nor do they necessarily limit the scope of the invention. Other features of the present invention will become apparent from the following description.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the description below are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flowchart of a training method of a battery resting time prediction model according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a battery capacity test in accordance with an embodiment of the present invention;
fig. 3 is a flowchart of a battery resting time prediction method according to a second embodiment of the present invention;
fig. 4 is a schematic structural diagram of a training device of a battery resting time prediction model according to a third embodiment of the present invention;
fig. 5 is a schematic structural diagram of a battery resting time prediction apparatus according to a fourth embodiment of the present invention;
fig. 6 is a schematic structural diagram of an electronic device according to a fifth embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the 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 invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein.
The names of messages or information exchanged between devices in the embodiments of the present disclosure are for illustrative purposes only, and are not intended to limit the scope of the messages or information.
It is understood that before the technical solutions disclosed in the embodiments of the present disclosure are used, the type, the use range, the use scene, etc. of the personal information related to the present disclosure should be informed to the user and obtain the authorization of the user through a proper manner according to the relevant laws and regulations.
For example, in response to receiving a user's active request, prompt information is sent to the user to explicitly prompt the user that the requested operation to be performed would require acquisition and use of personal information to the user. Thus, the user can autonomously select whether to provide personal information to software or hardware such as an electronic device, an application program, a server, or a storage medium that performs the operations of the disclosed technical solution, according to the prompt information.
As an optional but non-limiting implementation manner, in response to receiving an active request from the user, the manner of sending the prompt information to the user may be, for example, a pop-up window, and the prompt information may be presented in a text manner in the pop-up window. In addition, a selection control for providing personal information to the electronic device by the user's selection of "agreeing" or "disagreeing" can be carried in the pop-up window.
It is understood that the above notification and user authorization process is only illustrative and not limiting, and other ways of satisfying relevant laws and regulations may be applied to the implementation of the present disclosure.
It will be appreciated that the data involved in the subject technology, including but not limited to the data itself, the acquisition or use of the data, should comply with the requirements of the corresponding laws and regulations and related regulations.
Example one
Fig. 1 is a flowchart of a method for training a battery standing time prediction model according to an embodiment of the present invention, where the method is applicable to a situation where a standing time of a battery in a capacity test process is determined, and the method can be executed by a training device of the battery standing time prediction model, the training device of the battery standing time prediction model can be implemented in a form of hardware and/or software, and the training device of the battery standing time prediction model can be configured in an intelligent terminal and a cloud server.
The test of the battery capacity is generally divided into a charging stage and a discharging stage, and after the battery is charged, the capacity of the battery can be calculated according to the discharging time and the current. Usually, a rest phase is also included between the charging phase and the discharging phase. In other words, in the process of testing the battery capacity, after the battery is charged, the battery needs to be left for a period of time before being discharged. It should be noted that, in the same charging process, the discharge capacity test is performed after the battery is left standing for 10min and left standing for 1h, the difference between the obtained battery capacity test results is 2% to 5%, and the specific error can be determined according to the self-discharge performance of the battery. At the present stage, the standing time is estimated approximately according to the experience of the test and the materials, types and the like of the battery, namely the standing time of the battery in the capacity test process cannot be accurately determined. Based on the above, since there is a certain error in the estimated standing time, the prediction result is inaccurate, and thus the reliability of the test result is reduced. In order to solve the above problem, an embodiment of the present invention provides a training method for a battery standing time prediction model, so as to obtain a prediction model capable of accurately predicting battery standing time based on the training method, thereby improving reliability of a prediction result. Specifically, as shown in fig. 1, the training method of the battery standing time prediction model specifically includes:
s110, sample batteries used for model training are obtained, and battery type data corresponding to the sample batteries respectively are determined.
In the embodiment of the invention, because different types of batteries have different battery characteristics, in order to enable the trained battery standing time prediction model to predict the standing time of various types of batteries in the capacity testing process, the sample battery for training needs to comprise different types of batteries. It should be noted that different types of batteries may be understood as batteries with different materials, may also be understood as batteries with different nominal capacity values, and may of course be other different types of batteries.
Specifically, the battery subjected to the battery capacity test may be used as a sample battery for model training, and of course, different types of batteries may be obtained based on other manners as sample batteries for model training. On the basis of acquiring each sample battery for training, corresponding battery type data can be determined based on the battery label of each sample battery; optionally, the battery may be tested based on preset battery testing equipment to obtain type data of the sample battery.
It should be noted that the above manners of acquiring the sample battery and determining the battery type data corresponding to the sample battery are all exemplary embodiments of the present invention, and are not intended to limit the embodiments of the technical solution of the present invention.
And S120, determining battery capacity data corresponding to each sample battery in the capacity testing process.
In this embodiment, the battery capacity data may be understood as storage data of the battery during the capacity test process, and specifically includes, but is not limited to, capacity data such as test time, execution serial number, execution name, voltage, current, power, stage charging energy, stage discharging energy, stage charging capacity, stage discharging capacity, charging energy, discharging energy, charging capacity, and discharging capacity. It should be noted that, for each battery capacity data, the data that can be directly acquired includes current data and voltage data, and the data other than the current data and the voltage data is calculated by a preset calculation formula.
Optionally, in this embodiment, the method for determining battery capacity data respectively corresponding to each sample battery in the capacity test process includes: acquiring current data and voltage data of each sample battery in the capacity test process; and determining battery capacity data corresponding to each sample battery based on the current data and the voltage data.
Specifically, different battery capacity data need to be obtained through different calculation formulas. Based on the above, on the basis of obtaining the current data and the voltage data of the sample battery in the capacity test process, respectively corresponding battery capacity data are obtained based on corresponding calculation formulas.
In this embodiment, in the history process of carrying out battery capacity test to the sample battery based on charging and discharging equipment, thereby because there is the connecting wire formation line resistance between charging and discharging equipment and the battery under test, so there is the error between the voltage data and the voltage data of the battery inside that the battery management system based on charging and discharging equipment and acquireed voltage and current data and battery under test acquireed, and the connecting wire of different length can form the line resistance of equidimension not between charging and discharging equipment and the battery under test, the error has further been increased, thereby lead to there being the error in each battery capacity data that leads to calculating based on current data and voltage data, and then lead to reducing the accuracy based on the battery standing time prediction model that this training obtained.
In order to reduce the error of the obtained battery capacity data, the technical scheme of the embodiment adds the acquisition device between the charging and discharging equipment and the sample battery. Specifically, as shown in fig. 2, the collecting device includes a current collecting device and a voltage collecting device, which are respectively used for collecting voltage data and current data of the sample battery during the capacity test process, and storing the voltage data and the current data obtained inside the battery and the voltage data and the current data obtained by the charging and discharging device in the computer recording software. And calculating the voltage data and the current data based on computer recording software to obtain the battery capacity data of the sample battery, and storing the battery capacity data in a database for storage. The operation has the effect that the battery capacity data stored in the database is directly extracted to serve as training data to train the battery standing time prediction model, so that the efficiency and the accuracy of the battery standing time prediction model obtained based on the training are improved.
Optionally, in this embodiment, the method for obtaining current data and voltage data of each sample battery in the capacity test process may include: for any sample battery, reading system current data and system voltage data of the current sample battery based on a preset battery management system; acquiring current data and voltage data of a current sample battery based on a preset data acquisition device; and obtaining the test current data and the test voltage data of the current sample battery based on the charging and discharging equipment in the capacity test process.
Optionally, in this embodiment, the method for determining the battery capacity data corresponding to each sample battery based on the current data and the voltage data may include: for any sample battery, determining system battery capacity data of the current sample battery based on the system current data and the system voltage data; determining the collected battery capacity data of the current sample battery based on the collected current data and the collected voltage data; determining test battery capacity data of the current sample battery based on the test current data and the test voltage data; and determining the battery capacity data of the current sample battery based on the system battery capacity data, the collected battery capacity data and the test battery capacity data.
Specifically, on the basis of obtaining the current data and the voltage data corresponding to each obtaining mode, the current data and the voltage data are calculated based on a preset calculation formula to obtain battery capacity data corresponding to each obtaining mode, and it should be noted that the obtained battery capacity data are correspondingly different according to different calculation formulas.
And S130, training the standing time prediction model based on the battery capacity data and the battery type data respectively corresponding to each sample battery to obtain the trained standing time prediction model.
For a battery that determines the type of the battery, the resting time of the battery may be determined in the case of determining the charging data of the battery, so that the battery is rested. Therefore, in order to reduce the amount of data calculation, the acquired battery capacity data of each sample battery in the capacity testing process includes the charged battery capacity data corresponding to the charging phase and the stationary battery capacity data corresponding to the stationary phase.
On the basis, in this embodiment, the method for training the static time prediction model based on the battery capacity data and the battery type data respectively corresponding to each sample battery to obtain the trained static time prediction model may include: for any sample battery, determining rechargeable battery capacity data and static battery capacity data corresponding to the battery type data of the battery sample based on a preset battery corresponding relation; and taking the battery type data, the rechargeable battery capacity data and the static battery capacity data as sample training data of the current sample battery, and training the static time prediction model to obtain the trained static time prediction model.
Specifically, the battery type data, the rechargeable battery capacity data and the static battery capacity data are used as sample training data of the current sample battery and input into a battery static time prediction model to be trained, and a capacity prediction value output by the model is obtained. And acquiring a historical capacity value in a historical capacity test result corresponding to the current sample battery, and taking the historical capacity value as a label of the current sample battery in the training process. And generating a loss function of the model in the iterative training process based on the label and the capacity predicted value output by the model, adjusting model parameters of the battery standing time prediction model based on the loss function, and stopping training when the training meets the iterative stopping condition to obtain the trained standing time prediction model. Optionally, the standing time prediction model may be used to predict the standing time of the battery in the standing stage during the capacity test.
On the basis of the foregoing embodiment, in order to eliminate the unit limitation of the input data and facilitate comparing and weighting data of different magnitudes or units, the embodiment of the present invention performs normalization processing on the battery type data and the battery capacity data in the input data by using a maximum and minimum normalization method. The operation has the effects that on one hand, the convergence speed of the model can be accelerated, and on the other hand, the prediction precision of the model can be improved.
The technical scheme of the embodiment of the invention specifically comprises the following steps: obtaining sample batteries for model training, and determining battery type data corresponding to each sample battery; determining battery capacity data respectively corresponding to each sample battery in the capacity testing process; training the standing time prediction model based on battery capacity data and battery type data respectively corresponding to each sample battery to obtain a trained standing time prediction model; the standing time prediction model is used for predicting the standing time of the battery in the standing stage in the capacity test process. According to the technical scheme, the battery standing time prediction model is trained by obtaining the type data of the sample battery and the battery capacity data in the capacity testing process, so that the trained battery standing time prediction model is obtained, the problem that the efficiency and the accuracy of the test are affected by the standing time obtained by estimation in the prior art is solved, the accurate standing time is provided, and the accuracy of the test result is improved.
On the basis of the above embodiment, the embodiment of the present invention further provides a preferred embodiment, which is used to specifically introduce a training method of a battery resting time prediction model. The specific steps of this embodiment include:
the charging and discharging equipment tests the capacity by charging and discharging the battery, an external independent voltage and current acquisition device is newly added, and a plurality of data are combined based on the voltage and the current in the process for recording and storing, wherein the data comprise test time, execution serial number, execution name, voltage, current, power, stage charging energy, stage discharging energy, stage charging capacity, stage discharging capacity, charging capacity, discharging energy, charging capacity, discharging capacity, stage time, accumulated time, data content reported by a battery management system and the like. Meanwhile, the voltage and current acquired by the external acquisition device can be subjected to weighted analysis with the voltage and current acquired by the charging and discharging equipment and the voltage and current reported by the battery management system to offset the voltage inconsistency caused by the line length.
According to different battery capacity data and different battery types, starting from the stored database based on the battery capacity charge-discharge test standing time data, preprocessing and extracting the content data (charging + standing) of the standing step and the previous step, and deleting or interpolating if missing data occurs by taking the corresponding time and voltage in the battery capacity test charging + standing step and the data of the nominal capacity and the battery type as input characteristics. And training the deep neural network model by adopting different battery capacities and types to obtain a trained model, wherein the trained model can predict all standing time.
Specifically, the training process comprises:
step 1: in order to eliminate the unit limitation of the data characteristics and facilitate the comparison and weighting of data with different magnitudes or units, the maximum and minimum normalization method is adopted to perform normalization processing on all the data characteristics. On one hand, the convergence speed of the model can be accelerated, and on the other hand, the prediction precision of the model can be improved.
And 2, step: 80% of them were randomly selected as training set and the rest as test set.
And step 3: training a deep neural network by BP algorithm using training set data while setting weights (W) and bias values (b)
And 4, step 4: and inputting the test set into the deep neural network prediction model, verifying whether the model has an over-fitting problem, and testing the accuracy and the applicability of the prediction model.
Example two
Fig. 3 is a flowchart of a battery standing time prediction method according to a second embodiment of the present invention, where the method is applicable to determining a standing time of a battery in a standing stage during a capacity test process, and the method may be executed by a battery standing time prediction apparatus, the battery standing time prediction apparatus may be implemented in a form of hardware and/or software, and the battery standing time prediction apparatus may be configured in an intelligent terminal and a cloud server. As shown in fig. 3, the method includes:
s210, acquiring the target battery and determining the battery type data of the target battery.
In the embodiment of the present invention, the target battery may be understood as a battery that is undergoing a battery capacity test. Specifically, the method for determining the battery type data of the target battery may include: determining corresponding battery type data based on the battery label of each sample battery; optionally, the determining method may further include: and testing the battery based on preset battery testing equipment to obtain the type data of the sample battery.
And S220, determining the corresponding rechargeable battery capacity data of the target battery in the charging stage in the capacity testing process.
Specifically, current data and voltage data of the target battery in a charging stage are determined, and the capacity data of the rechargeable battery is obtained based on the current data and the voltage data. Specifically, system current data and system voltage data in a target battery are read based on a preset battery management system, and system battery capacity data of the target battery are determined based on the system current data and the system voltage data; acquiring current data and voltage data of a target battery based on a preset data acquisition device, and determining the acquired battery capacity data of the target battery based on the current data and the voltage data; acquiring test current data and test voltage data of a target battery based on charge and discharge equipment in a capacity test process, and determining test battery capacity data of the target battery based on the test current data and the test voltage data; and determining the battery capacity data of the target battery based on the system battery capacity data, the collected battery capacity data and the test battery capacity data.
And S230, inputting the capacity data and the battery type data of the rechargeable battery into a pre-trained battery standing time prediction model to obtain the standing time of the target battery in a standing stage in the capacity testing process.
According to the technical scheme of the embodiment of the invention, the battery standing time prediction model is trained by obtaining the type data of the sample battery and the battery capacity data in the capacity testing process to obtain the trained battery standing time prediction model, and the standing time of the target battery in the battery capacity testing process is predicted by adopting the trained battery standing time prediction model, so that the problem that the efficiency and the accuracy of the test are influenced by the estimated standing time in the prior art is solved, the accurate standing time is provided, and the accuracy of the test result is improved.
EXAMPLE III
Fig. 4 is a schematic structural diagram of a training device of a battery resting time prediction model according to a third embodiment of the present invention. As shown in fig. 4, the apparatus includes: a sample battery acquisition module 310, a sample battery acquisition module 320, and a model training module 330; wherein, the first and the second end of the pipe are connected with each other,
a sample battery obtaining module 310, configured to obtain sample batteries for model training, and determine battery type data corresponding to each sample battery;
a battery capacity data obtaining module 320, configured to determine battery capacity data corresponding to each sample battery in a capacity testing process;
the model training module 330 is configured to train the standing time prediction model based on battery capacity data and battery type data respectively corresponding to each sample battery to obtain a trained standing time prediction model; the standing time prediction model is used for predicting the standing time of the battery in the standing stage in the capacity test process.
Optionally, on the basis of the foregoing embodiment, the battery capacity data obtaining module 320 includes:
the data acquisition submodule is used for acquiring current data and voltage data of each sample battery in the capacity test process;
and the battery capacity data determining submodule is used for determining battery capacity data corresponding to each sample battery based on the current data and the voltage data.
Optionally, on the basis of the foregoing embodiment, the data obtaining sub-module includes:
the system comprises a system data acquisition unit, a battery management unit and a control unit, wherein the system data acquisition unit is used for reading system current data and system voltage data of a current sample battery based on a preset battery management system for any sample battery;
the acquisition data acquisition unit is used for acquiring the current acquisition current data and the voltage acquisition data of the current sample battery based on a preset data acquisition device;
and the test data acquisition unit is used for acquiring the test current data and the test voltage data of the current sample battery based on the charging and discharging equipment in the capacity test process.
Optionally, the battery capacity data determining sub-module based on the foregoing embodiment includes:
the system battery capacity data determining unit is used for determining the system battery capacity data of the current sample battery for any sample battery based on the system current data and the system voltage data;
the collected battery capacity data determining unit is used for determining the collected battery capacity data of the current sample battery based on the collected current data and the collected voltage data;
the test battery capacity data determining unit is used for determining the test battery capacity data of the current sample battery based on the test current data and the test voltage data;
and the battery capacity data determining unit is used for determining the battery capacity data of the current sample battery based on the system battery capacity data, the acquired battery capacity data and the test battery capacity data.
Optionally, on the basis of the foregoing embodiment, the battery capacity data of each sample battery in the capacity testing process includes charging battery capacity data corresponding to a charging phase and standing battery capacity data corresponding to a standing phase;
accordingly, model training module 330 includes:
the stage battery capacity data determining submodule is used for determining the rechargeable battery capacity data and the static battery capacity data corresponding to the battery type data of any sample battery based on a preset battery corresponding relation;
and the model training submodule is used for training the standing time prediction model by taking the battery type data, the rechargeable battery capacity data and the standing battery capacity data as sample training data of the current sample battery to obtain the trained standing time prediction model.
The training device for the battery standing time prediction model provided by the embodiment of the invention can execute the training method for the battery standing time prediction model provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.
Example four
Fig. 5 is a schematic structural diagram of a training device of a battery resting time prediction model according to a fourth embodiment of the present invention. As shown in fig. 5, the apparatus includes:
a rechargeable battery capacity data acquisition module 410, configured to acquire rechargeable battery capacity data corresponding to a charging stage of a target battery in a capacity test process;
a standing time obtaining module 420, configured to input the rechargeable battery capacity data into a pre-trained battery standing time prediction model, so as to obtain a standing time of the target battery in a standing stage in a capacity testing process; the battery standing time prediction model is obtained by training based on the training method of the battery standing time prediction model in any embodiment.
The training device for the battery standing time prediction model provided by the embodiment of the invention can execute the training method for the battery standing time prediction model provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.
EXAMPLE five
FIG. 6 illustrates a block diagram of an electronic device 10 that may be used to implement an embodiment of the invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.
As shown in fig. 6, the electronic device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, and the like, wherein the memory stores a computer program executable by the at least one processor, and the processor 11 can perform various suitable actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from a storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data necessary for the operation of the electronic apparatus 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.
A number of components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, or the like; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.
The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, or the like. The processor 11 executes the above-described respective methods and processes, such as the training method of the battery rest time prediction model and the battery rest time prediction method.
In some embodiments, the method of training the battery rest time prediction model and the battery rest time prediction method may be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the above-described training method of the battery rest time prediction model and the battery rest time prediction method may be performed. Alternatively, in other embodiments, processor 11 may be configured by any other suitable means (e.g., by means of firmware) to perform the training method of the battery rest time prediction model and the battery rest time prediction method.
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
A computer program for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be performed. A computer program can execute entirely on a machine, partly on a machine, as a stand-alone software package partly on a machine and partly on a remote machine or entirely on a remote machine or server.
In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.
The computing system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical host and VPS service are overcome.
It should be understood that various forms of the flows shown above, reordering, adding or deleting steps, may be used. For example, the steps described in the present invention may be executed in parallel, sequentially, or in different orders, and are not limited herein as long as the desired results of the technical solution of the present invention can be achieved.
The above-described embodiments should not be construed as limiting the scope of the invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A training method of a battery standing time prediction model is characterized by comprising the following steps:
obtaining sample batteries for model training, and determining battery type data corresponding to each sample battery;
determining battery capacity data respectively corresponding to each sample battery in a capacity test process;
training the standing time prediction model based on battery capacity data and battery type data respectively corresponding to the sample batteries to obtain a trained standing time prediction model; the standing time prediction model is used for predicting the standing time of the battery in the standing stage in the capacity test process.
2. The method of claim 1, wherein the determining battery capacity data corresponding to each of the sample batteries during the capacity testing process comprises:
acquiring current data and voltage data of each sample battery in a capacity test process;
and determining battery capacity data corresponding to the sample batteries respectively based on the current data and the voltage data.
3. The method of claim 2, wherein said obtaining current data and voltage data for each of said sample cells during a capacity test comprises:
for any sample battery, reading system current data and system voltage data of the current sample battery based on a preset battery management system;
acquiring current data and voltage data of the current sample battery based on a preset data acquisition device;
and acquiring the test current data and the test voltage data of the current sample battery based on the charging and discharging equipment in the capacity test process.
4. The method of claim 3, wherein the determining battery capacity data corresponding to each of the sample batteries based on the current data and the voltage data comprises:
for any sample battery, determining system battery capacity data of the current sample battery based on the system current data and the system voltage data;
determining collected battery capacity data of the current sample battery based on the collected current data and the collected voltage data;
determining test battery capacity data of the current sample battery based on the test current data and the test voltage data;
and determining the battery capacity data of the current sample battery based on the system battery capacity data, the acquired battery capacity data and the test battery capacity data.
5. The method according to claim 1, wherein the battery capacity data of each sample battery in the capacity testing process comprises charging battery capacity data corresponding to a charging stage and standing battery capacity data corresponding to a standing stage;
correspondingly, the training of the standing time prediction model based on the battery capacity data and the battery type data respectively corresponding to each sample battery to obtain a trained standing time prediction model includes:
for any sample battery, determining the rechargeable battery capacity data and the static battery capacity data corresponding to the battery type data of the battery sample based on a preset battery corresponding relation;
and taking the battery type data, the rechargeable battery capacity data and the static battery capacity data as sample training data of the current sample battery, and training the static time prediction model to obtain a trained static time prediction model.
6. A method for predicting a battery standing time, comprising:
acquiring a target battery and determining battery type data of the target battery;
determining the corresponding rechargeable battery capacity data of the target battery in the charging stage in the capacity testing process;
inputting the capacity data of the rechargeable battery and the type data of the battery into a pre-trained battery standing time prediction model to obtain the standing time of the target battery in a standing stage in the capacity testing process; wherein the battery standing time prediction model is obtained by training based on the training method of the battery standing time prediction model according to any one of claims 1 to 5.
7. A training device for a battery standing time prediction model is characterized by comprising:
the system comprises a sample battery acquisition module, a model training module and a control module, wherein the sample battery acquisition module is used for acquiring sample batteries used for model training and determining battery type data corresponding to each sample battery;
the battery capacity data acquisition module is used for determining battery capacity data corresponding to each sample battery in the capacity test process;
the model training module is used for training the standing time prediction model based on battery capacity data and battery type data which respectively correspond to each sample battery to obtain a trained standing time prediction model; the standing time prediction model is used for predicting the standing time of the battery in the standing stage in the capacity test process.
8. A battery rest time prediction apparatus, comprising:
the system comprises a rechargeable battery capacity data acquisition module, a capacity test module and a capacity test module, wherein the rechargeable battery capacity data acquisition module is used for acquiring rechargeable battery capacity data corresponding to a target battery in a charging stage in a capacity test process;
the standing time obtaining module is used for inputting the capacity data of the rechargeable battery into a pre-trained battery standing time prediction model to obtain the standing time of the target battery in a standing stage in the capacity testing process; wherein the battery standing time prediction model is obtained by training based on the training method of the battery standing time prediction model according to any one of claims 1 to 5.
9. An electronic device, characterized in that the electronic device comprises:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein, the first and the second end of the pipe are connected with each other,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform a method of training a battery rest time prediction model according to any one of claims 1 to 5, and/or a method of predicting battery rest time according to claim 6.
10. A computer-readable storage medium storing computer instructions for causing a processor to implement a method of training a battery rest time prediction model according to any one of claims 1 to 5 and/or a method of predicting battery rest time according to claim 6 when executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210927520.1A CN115291111B (en) | 2022-08-03 | 2022-08-03 | Training method of battery rest time prediction model and rest time prediction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210927520.1A CN115291111B (en) | 2022-08-03 | 2022-08-03 | Training method of battery rest time prediction model and rest time prediction method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115291111A true CN115291111A (en) | 2022-11-04 |
| CN115291111B CN115291111B (en) | 2023-09-29 |
Family
ID=83825474
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210927520.1A Active CN115291111B (en) | 2022-08-03 | 2022-08-03 | Training method of battery rest time prediction model and rest time prediction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115291111B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102006061523A1 (en) * | 2006-12-20 | 2008-06-26 | Fachhochschule Nordhausen Körperschaft des öffentlichen Rechts | Method for diagnosing technical systems, involves subjecting technical system to diagnosis and placing two time synchronized reading recorders without engaging in concerned system, which record temporal process of measuring parameters |
| CN105808914A (en) * | 2014-12-31 | 2016-07-27 | 北京航天测控技术有限公司 | Method and device for predicting life of satellite lithium ion battery |
| CN108072848A (en) * | 2018-01-31 | 2018-05-25 | 胡继业 | Estimate the analysis method of battery discharging duration |
| CN108139446A (en) * | 2015-10-15 | 2018-06-08 | 江森自控科技公司 | For predicting the battery test system of cell testing results |
| US20200011932A1 (en) * | 2018-07-05 | 2020-01-09 | Nec Laboratories America, Inc. | Battery capacity fading model using deep learning |
| CN111896883A (en) * | 2020-07-30 | 2020-11-06 | 重庆长安汽车股份有限公司 | Vehicle-mounted storage battery supportable parking time prediction method and early warning method |
| CN112874369A (en) * | 2021-01-12 | 2021-06-01 | 上海追日电气有限公司 | Charging and energy supply optimization method and device of charging management system |
| CN113743661A (en) * | 2021-08-30 | 2021-12-03 | 西安交通大学 | Method, system, equipment and storage medium for predicting online capacity of lithium ion battery |
-
2022
- 2022-08-03 CN CN202210927520.1A patent/CN115291111B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102006061523A1 (en) * | 2006-12-20 | 2008-06-26 | Fachhochschule Nordhausen Körperschaft des öffentlichen Rechts | Method for diagnosing technical systems, involves subjecting technical system to diagnosis and placing two time synchronized reading recorders without engaging in concerned system, which record temporal process of measuring parameters |
| CN105808914A (en) * | 2014-12-31 | 2016-07-27 | 北京航天测控技术有限公司 | Method and device for predicting life of satellite lithium ion battery |
| CN108139446A (en) * | 2015-10-15 | 2018-06-08 | 江森自控科技公司 | For predicting the battery test system of cell testing results |
| CN108072848A (en) * | 2018-01-31 | 2018-05-25 | 胡继业 | Estimate the analysis method of battery discharging duration |
| US20200011932A1 (en) * | 2018-07-05 | 2020-01-09 | Nec Laboratories America, Inc. | Battery capacity fading model using deep learning |
| CN111896883A (en) * | 2020-07-30 | 2020-11-06 | 重庆长安汽车股份有限公司 | Vehicle-mounted storage battery supportable parking time prediction method and early warning method |
| CN112874369A (en) * | 2021-01-12 | 2021-06-01 | 上海追日电气有限公司 | Charging and energy supply optimization method and device of charging management system |
| CN113743661A (en) * | 2021-08-30 | 2021-12-03 | 西安交通大学 | Method, system, equipment and storage medium for predicting online capacity of lithium ion battery |
Non-Patent Citations (4)
| Title |
|---|
| KAI HUANG ET AL.: "A Novel Health Factor to Predict the Battery’s State-of-Health Using a Support Vector Machine Approach", APPLIED SCIENCES, vol. 8, no. 10 * |
| 李练兵 等: "基于差分电压和Elman神经网络的锂离子电池RUL预测方法", 储能科学与技术, vol. 10, no. 6 * |
| 胡任;韩赞东;王克争;: "基于BP神经网络预测静置电池的剩余电量", 电池, no. 01 * |
| 董汉 等: "危险驾驶工况场景的复杂度评估方法研究", 汽车工程, vol. 42, no. 6 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115291111B (en) | 2023-09-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115221795A (en) | Training method, prediction method, device, equipment and medium of capacity prediction model | |
| WO2018112818A1 (en) | Rapid prediction method for cycle life of battery and rapid prediction device therefor | |
| CN114500339B (en) | Node bandwidth monitoring method and device, electronic equipment and storage medium | |
| CN115932634A (en) | Method, device, equipment and storage medium for evaluating health state of battery | |
| CN114954105A (en) | Battery replacement method and device, electronic equipment and storage medium | |
| CN115372841A (en) | Method and device for evaluating thermal runaway risk of lithium ion battery monomer | |
| CN117129879B (en) | Threshold adjustment method and training method of battery state of health prediction model | |
| CN115754772A (en) | Battery capacity attenuation processing method, device, equipment and storage medium | |
| CN115902625A (en) | Performance prediction method, device, equipment and storage medium of battery system | |
| CN115291111B (en) | Training method of battery rest time prediction model and rest time prediction method | |
| CN115395613A (en) | Battery charging management method and device, electronic equipment and storage medium | |
| CN115692885A (en) | Battery lithium separation protection method and device, electronic equipment and storage medium | |
| CN114779109A (en) | Method and device for determining battery health state, electronic equipment and storage medium | |
| CN113433478A (en) | Method and device for estimating health degree of power battery by cloud | |
| CN117706390B (en) | Rolling optimization estimation method and device for battery state of charge | |
| CN115792628A (en) | Power battery safety evaluation method, device, equipment and storage medium | |
| CN117805621A (en) | Battery capacity estimation method, device, equipment and storage medium | |
| CN116027197A (en) | Method, device, equipment and storage medium for evaluating self-discharge consistency of battery | |
| CN115333209A (en) | Battery management method and device, storage medium and electronic equipment | |
| CN115902651A (en) | Power battery testing method, device, equipment and storage medium | |
| CN117420468A (en) | Battery state evaluation method, device, equipment and storage medium | |
| CN116819342A (en) | Battery life curve determining method and device, electronic equipment and storage medium | |
| CN115015806A (en) | Battery cell short circuit judgment method and device and storage medium | |
| CN117907847A (en) | Abnormal battery screening method, device, equipment and storage medium | |
| CN116087807A (en) | Method and device for testing battery charging cut-off voltage, electronic equipment and storage medium |
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 |