CN114355224B - Battery health state prediction method and device, electronic device and readable storage medium - Google Patents
Battery health state prediction method and device, electronic device and readable storage medium Download PDFInfo
- Publication number
- CN114355224B CN114355224B CN202210262758.7A CN202210262758A CN114355224B CN 114355224 B CN114355224 B CN 114355224B CN 202210262758 A CN202210262758 A CN 202210262758A CN 114355224 B CN114355224 B CN 114355224B
- Authority
- CN
- China
- Prior art keywords
- state
- battery
- health
- track
- observation data
- 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
Abstract
The application relates to a battery state of health prediction method, a device, an electronic device and a readable storage medium, wherein the method comprises the following steps: acquiring observation data of a current battery, and acquiring a plurality of battery state tracks from a battery database; generating a state prediction track of the current battery based on the observation data and the plurality of battery state tracks; and predicting the health state of the current battery according to the observation data and the state prediction track. The state prediction track is generated based on the actual observation data of the current battery and the historical battery state track, so that the obtained state prediction track can be more fit with the actual state of the current battery, and the prediction operation based on the state prediction track is more accurate.
Description
Technical Field
The present disclosure relates to the field of battery management, and more particularly, to a method and an apparatus for predicting a battery health status, an electronic apparatus, and a readable storage medium.
Background
Various methods for battery SoH (State Of Health) prediction have been proposed in the prior art; such as similarity-based methods, fuzzy logic, neural networks, and the like; however, one common drawback of these approaches is the large amount of historical data required to describe the uncertainty of the prediction and the ability to adapt to the process dynamics. To solve this problem, prediction is mostly performed by a method based on gaussian process regression, particle filters and a correlation vector machine, which, although it can effectively describe the uncertainty of prediction, cannot be robust to the variations between different batteries subjected to different usage patterns; this allows for more accurate predictions only in the offline phase, and less accurate predictions in the online phase.
Disclosure of Invention
The application provides a method and a device for predicting the state of health of a battery, an electronic device and a readable storage medium, and aims to solve the technical problem that how to have robustness on the change between different batteries in the prior art.
In order to solve the technical problem described above or at least partially solve the technical problem described above, the present application provides a battery state of health prediction method, including the steps of:
acquiring observation data of a current battery, and acquiring a plurality of battery state tracks from a battery database;
generating a state prediction track of the current battery based on the observation data and a plurality of battery state tracks;
and predicting the health state of the current battery according to the observation data and the state prediction track.
Optionally, the step of generating a state prediction track of the current battery based on the observation data and the plurality of battery state tracks includes:
obtaining correlation parameters between the observation data and each battery state track;
and generating a state prediction track of the current battery through a plurality of battery state tracks and the corresponding correlation parameters.
Optionally, the step of obtaining a correlation parameter between the observation data and each battery state track includes:
Acquiring a trained correlation model, and taking the observation data and the battery state tracks as the input of the trained correlation model;
and operating the trained correlation model to obtain correlation parameters between the observation data and each battery state track.
Optionally, the step of obtaining a trained relevance model is preceded by:
establishing a relation model expressed by mean function and covariance of Gaussian distribution based on the observation data and the battery state track;
obtaining model parameters, wherein the model parameters comprise hyper-parameters of a mean function and hyper-parameters of a covariance function;
establishing an initial correlation model based on the relationship model and the model parameters;
and training the initial correlation model to obtain a trained correlation model.
Optionally, the step of training the initial correlation model to obtain a trained correlation model includes:
the mean function and the unknown parameters of the covariance function are estimated by a negative log-edge likelihood function in a maximization equation.
Optionally, the observation data includes a usage time of the current battery, and the state prediction trajectory is a trajectory reflecting a change in a state of health of the battery based on the usage time; the step of predicting the state of health of the current battery through the observation data and the state prediction track comprises:
Substituting the using time into the state prediction track to obtain a track health state corresponding to the using time in the state prediction track;
taking the trajectory state of health as the predicted state of health of the current battery.
Optionally, the step of obtaining a plurality of battery status tracks from a battery database is followed by:
performing dynamic time warping on each battery state track to enable the lengths of the battery state tracks to be consistent;
and adjusting the sample point in each battery state track to be the ratio of the actual capacity to the rated capacity.
In order to achieve the above object, the present invention also provides a battery state of health predicting apparatus, including:
the first acquisition module is used for acquiring observation data of a current battery and acquiring a plurality of battery state tracks from a battery database;
a first generation module, configured to generate a state prediction trajectory of the current battery based on the observation data and the plurality of battery state trajectories;
and the first execution module is used for predicting the health state of the current battery through the observation data and the state prediction track.
Optionally, the first generating module comprises:
the first acquisition submodule is used for acquiring correlation parameters between the observation data and the battery state tracks;
the first generation submodule is used for generating a state prediction track of the current battery through a plurality of battery state tracks and the corresponding correlation parameters.
Optionally, the first obtaining sub-module includes:
the first acquisition unit is used for acquiring trained correlation models and taking the observation data and the battery state tracks as the input of the trained correlation models;
and the first execution unit is used for operating the trained correlation model to obtain correlation parameters between the observation data and the battery state tracks.
Optionally, the first obtaining sub-module further includes:
the second execution unit is used for establishing a relation model expressed by mean function and covariance of Gaussian distribution based on the observation data and the battery state track;
the second acquisition unit is used for acquiring model parameters, wherein the model parameters comprise hyper-parameters of a mean function and hyper-parameters of a covariance function;
a third execution unit, configured to establish an initial correlation model based on the relationship model and the model parameters;
And the first training unit is used for training the initial correlation model to obtain a trained correlation model.
Optionally, the first training unit comprises:
a first execution subunit, configured to estimate the unknown parameters of the mean function and the covariance function by maximizing a negative log-edge likelihood function in an equation.
Optionally, the observation data includes a usage time of the current battery, and the state prediction trajectory reflects a change in a state of health of the battery based on the usage time; the first execution module comprises:
the first execution submodule is used for substituting the using time into the state prediction track to obtain a track health state corresponding to the using time in the state prediction track;
a second execution submodule configured to use the trajectory health status as a predicted health status of the current battery.
Optionally, the battery state of health predicting apparatus further includes:
the third execution submodule is used for carrying out dynamic time warping on each battery state track so as to enable the lengths of each battery state track to be consistent;
and the fourth execution submodule is used for adjusting the sample point in each battery state track to be the ratio of the actual capacity to the rated capacity.
To achieve the above object, the present invention further provides an electronic device, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the battery health status prediction method as described above.
To achieve the above object, the present invention also provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the battery state of health prediction method as described above.
The invention provides a battery health state prediction method, a battery health state prediction device, an electronic device and a readable storage medium, which are used for acquiring observation data of a current battery and acquiring a plurality of battery state tracks from a battery database; generating a state prediction track of the current battery based on the observation data and a plurality of battery state tracks; and predicting the health state of the current battery according to the observation data and the state prediction track. The state prediction track is generated based on the actual observation data of the current battery and the historical battery state track, so that the obtained state prediction track can be more fit with the actual state of the current battery, and the prediction operation based on the state prediction track is more accurate.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without inventive exercise.
FIG. 1 is a schematic flow chart illustrating a method for predicting a state of health of a battery according to a first embodiment of the present invention;
fig. 2 is a detailed flowchart of step S20 of the battery state of health prediction method according to the second embodiment of the present invention;
fig. 3 is a schematic block diagram of an electronic device according to the present invention.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. In order to make the technical solutions better understood by those skilled in the art, 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 only partial 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.
The invention provides a method for predicting the state of health of a battery, referring to fig. 1, fig. 1 is a schematic flow diagram of a first embodiment of the method for predicting the state of health of the battery, and the method comprises the following steps:
step S10, obtaining the observation data of the current battery and obtaining a plurality of battery state tracks from the battery database;
the current battery is a battery needing to be subjected to state of health prediction; the observation data refers to the state parameter data of the battery observed in the current battery use process, and includes but is not limited to battery capacity, battery use time and the like; the battery state track represents the track of the change of the state of health of the battery along with time, the state of health can be reflected by the residual life, and the residual life refers to the ratio of the current capacity of the battery to the rated capacity; it should be noted that the battery state trajectory in the battery database may be actually measured, or may be historical data acquired from a server or a network.
Step S20, generating a state prediction track of the current battery based on the observation data and a plurality of battery state tracks;
and taking the battery state track as a reference, and taking the observation data as a basis for matching the battery state track with the current battery similarity, thereby finally obtaining the state prediction track of the current battery. The state prediction trajectory is used to describe a predicted trajectory of the current state of health of the battery over time.
And step S30, predicting the current state of health of the battery through the observation data and the state prediction track.
The use data of the current battery, such as the used time and the like, can be known through the observation data, so that the health state of the current battery can be predicted by matching the observation data in the state prediction track.
According to the method and the device, the state prediction track is generated based on the actual observation data of the current battery and the historical battery state track, so that the obtained state prediction track can be more fit with the actual state of the current battery, and the prediction operation based on the state prediction track is more accurate.
Further, referring to fig. 2, in the second embodiment of the battery state of health prediction method of the present invention proposed based on the first embodiment of the present invention, the step S20 includes the steps of:
step S21, obtaining correlation parameters between the observation data and each battery state track;
step S22, generating a state prediction trajectory of the current battery according to the plurality of battery state trajectories and the corresponding correlation parameters.
The performance, capacity, use condition and the like of different batteries are different, so that the change of the health states of different batteries is different, therefore, the correlation between different battery state tracks and the current battery needs to be determined, and the higher the correlation is, the more similar the battery state track is to the change of the health state of the current battery, and the more the health state of the current battery can be reflected through the battery state track; the correlation parameter is a parameter for reflecting the correlation between the battery state trajectory and the current battery. The state prediction trajectory in this embodiment can be expressed as:
Where y is the state prediction trajectory, TmFor the m-th cell state trace, αmCorrelation parameters corresponding to the mth battery state track; r is residual error term.
As can be seen from the above formula, in the present embodiment, the state prediction trajectory is modeled as a linear combination of a plurality of battery state trajectories, so that useful information of each battery state trajectory can be effectively utilized; meanwhile, the complexity of the model is reduced, so that the model reasoning can be efficiently realized.
The step S21 includes the steps of:
step S211, obtaining a trained correlation model, and taking the observation data and each battery state track as the input of the trained correlation model;
step S212, the trained correlation model is operated to obtain correlation parameters between the observation data and each battery state track.
In the embodiment, a correlation parameter is obtained through a correlation model, and the correlation model is specifically a gaussian process model; it should be noted that a suitable model may also be selected according to an actual application scenario and needs, and corresponding settings are performed, which are not described herein.
The step S211 is preceded by the step of:
step S213, establishing a relation model expressed by mean function and covariance of Gaussian distribution based on the observation data and the battery state track;
Step S214, obtaining model parameters, wherein the model parameters comprise hyper-parameters of a mean function and hyper-parameters of a covariance function;
step S215, establishing an initial correlation model based on the relation model and the model parameters;
and S216, training the initial correlation model to obtain a trained correlation model.
In this embodiment, a gaussian process is introduced to the model based on the state prediction trajectory to obtain a relationship model, which specifically includes:
wherein N is a normal distribution, k (x, x') is a kernel function, and T ism' is the SOC trajectory of the m-th cell.
The step S216 includes the steps of:
step S2161, the unknown parameters of the mean function and the covariance function are estimated by a negative log-edge likelihood function in the maximization equation.
In the model training process, the unknown parameters of the mean function and the covariance function are estimated by maximizing an NLML (Negative Log normalized likehood) in an equation; the method specifically comprises the following steps:
wherein L is a negative log-edge likelihood function, theta is a hyper-parameter of a mean function and a covariance function, p (y-x, theta) is an edge likelihood function, K is a kernel matrix, I is a unit matrix with the same size as K, and sigma is a unit matrix with the same size as K nFor noise standard deviation, T represents the matrix permutation, and m (x) is the mean function.
The hyper-parameters of the mean function and the hyper-parameters of the covariance function can be obtained through partial differential calculation; the method comprises the following specific steps:
wherein, thetamfA hyperparameter that is a mean function; theta.theta.mf=（α1，α2，…，αm）；
Wherein, thetacfIs a hyper-parameter of the covariance function.
The partial derivatives can be conveniently used in conjunction with a numerical optimization procedure, such as conjugate gradients, to find the optimal hyper-parameter setting. In this embodiment, a model is developed using GPML (Gaussian Machine Learning process) in MATLAB toolbox. Some precautions, such as cross-validation, are taken to prevent non-optimal local minima. It should be noted that, the specific development operation setting may be selected and executed in an analogy manner according to the actual application scenario and the need, and is not described herein again.
The embodiment can reasonably establish the Gaussian process model and obtain the correlation parameters.
Further, in a third embodiment of the battery state of health prediction method according to the present invention based on the first embodiment of the present invention, the observation data includes a usage time of the current battery, and the state prediction trajectory reflects a change in the state of health of the battery based on the usage time; the step S30 includes the steps of:
Step S31, substituting the use time into the state prediction track to obtain the track health state corresponding to the use time in the state prediction track;
and step S32, taking the track health state as the predicted health state of the current battery.
The state prediction track is used for representing the change process of the health state of the battery along with the use time; specifically, each use time corresponds to a health state in the state prediction track, and therefore, after the use time of the battery is obtained, the use time can be brought into the state prediction track to match the predicted health state.
The present embodiment can accurately predict the current state of health of the battery through the state prediction trajectory.
Further, in a fourth embodiment of the battery state of health prediction method of the present invention proposed based on the first embodiment of the present invention, the step S10 is followed by the step of:
step S40, performing dynamic time warping on each battery state track to enable the lengths of the battery state tracks to be consistent;
in step S50, the sample point in each battery state trajectory is adjusted to the ratio of the actual capacity to the rated capacity.
The lengths of the battery state tracks obtained are different due to the difference of the capacities and the service times of different batteries, and in order to facilitate the construction of the subsequent state prediction tracks, the battery state tracks are aligned to obtain the battery state tracks with the same length. Sampling parameters of the battery state tracks are different due to different sampling strategies of the different battery state tracks, so that the sampling parameters of the battery are required to be regularized, and the parameters of the battery state tracks are unified; specifically, in the present embodiment, a ratio of the actual capacity to the rated capacity is used as a sampling parameter; it should be noted that, the setting may also be performed according to the actual application scenario and the need, which is not described herein again.
The embodiment can obtain the battery state tracks with consistent length and uniform parameters.
It should be noted that, for simplicity of description, the above-mentioned method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present application is not limited by the order of acts described, as some steps may occur in other orders or concurrently depending on the application. Further, those skilled in the art should also appreciate that the embodiments described in the specification are preferred embodiments and that the acts and modules referred to are not necessarily required in this application.
Through the description of the foregoing embodiments, it is clear to those skilled in the art that the method according to the foregoing embodiments may be implemented by software plus a necessary general hardware platform, and certainly may also be implemented by hardware, but the former is a better implementation mode in many cases. Based on such understanding, the technical solutions of the present application may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present application.
The present application also provides a battery state of health predicting apparatus for implementing the above battery state of health predicting method, the battery state of health predicting apparatus including:
the first acquisition module is used for acquiring observation data of a current battery and acquiring a plurality of battery state tracks from a battery database;
a first generation module, configured to generate a state prediction trajectory of the current battery based on the observation data and the plurality of battery state trajectories;
And the first execution module is used for predicting the health state of the current battery through the observation data and the state prediction track.
The battery state of health prediction device generates the state prediction track through the actual observation data of the current battery and the historical battery state track, so that the obtained state prediction track can be more fit with the actual state of the current battery, and the prediction operation based on the state prediction track is more accurate.
It should be noted that the first obtaining module in this embodiment may be configured to execute step S10 in this embodiment, the first generating module in this embodiment may be configured to execute step S20 in this embodiment, and the first executing module in this embodiment may be configured to execute step S30 in this embodiment.
Further, the first generation module comprises:
the first obtaining submodule is used for obtaining correlation parameters between the observation data and each battery state track;
and the first generation submodule is used for generating a state prediction track of the current battery through a plurality of battery state tracks and the corresponding correlation parameters.
Further, the first obtaining sub-module includes:
The first acquisition unit is used for acquiring a trained correlation model and taking the observation data and each battery state track as the input of the trained correlation model;
and the first execution unit is used for operating the trained correlation model to obtain correlation parameters between the observation data and each battery state track.
Further, the first obtaining sub-module further includes:
the second execution unit is used for establishing a relation model expressed by mean function and covariance of Gaussian distribution based on the observation data and the battery state track;
the second acquisition unit is used for acquiring model parameters, wherein the model parameters comprise hyper-parameters of a mean function and hyper-parameters of a covariance function;
a third execution unit, configured to establish an initial correlation model based on the relationship model and the model parameters;
and the first training unit is used for training the initial correlation model to obtain a trained correlation model.
Further, the first training unit comprises:
a first execution subunit, configured to estimate the unknown parameters of the mean function and the covariance function by maximizing a negative log-edge likelihood function in an equation.
Further, the observation data includes the use time of the current battery, and the state prediction track is a track reflecting the change of the state of health of the battery based on the use time; the first execution module comprises:
the first execution submodule is used for substituting the use time into the state prediction track to obtain a track health state corresponding to the use time in the state prediction track;
a second execution submodule to use the track health status as a predicted current battery health status.
Further, the battery state of health prediction apparatus further includes:
the third execution submodule is used for carrying out dynamic time warping on each battery state track so as to enable the lengths of each battery state track to be consistent;
and the fourth execution submodule is used for adjusting the sample point in each battery state track to be the ratio of the actual capacity to the rated capacity.
It should be noted here that the modules described above are the same as the examples and application scenarios implemented by the corresponding steps, but are not limited to the disclosure of the above embodiments. The modules may be implemented by software as part of the apparatus, or may be implemented by hardware, where the hardware environment includes a network environment.
Referring to fig. 3, the electronic device may include components such as a communication module 10, a memory 20, and a processor 30 in a hardware configuration. In the electronic device, the processor 30 is connected to the memory 20 and the communication module 10, respectively, the memory 20 stores a computer program, the computer program is executed by the processor 30 at the same time, and the steps of the method embodiment are realized when the computer program is executed.
The communication module 10 may be connected to an external communication device through a network. The communication module 10 may receive a request from an external communication device, and may also send the request, an instruction, and information to the external communication device, where the external communication device may be another electronic apparatus, a server, or an internet of things device, such as a television.
The memory 20 may be used to store software programs and various data. The memory 20 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required for at least one function (such as obtaining observation data of a current battery), and the like; the storage data area may include a database, and the storage data area may store data or information created according to use of the system, or the like. Further, the memory 20 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device.
The processor 30, which is a control center of the electronic device, connects various parts of the entire electronic device using various interfaces and lines, performs various functions of the electronic device and processes data by operating or executing software programs and/or modules stored in the memory 20 and calling data stored in the memory 20, thereby integrally monitoring the electronic device. Processor 30 may include one or more processing units; alternatively, the processor 30 may integrate an application processor, which mainly handles operating systems, user interfaces, application programs, etc., and a modem processor, which mainly handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into the processor 30.
Although not shown in fig. 3, the electronic device may further include a circuit control module, which is used for connecting with a power supply to ensure the normal operation of other components. Those skilled in the art will appreciate that the electronic device configuration shown in fig. 3 does not constitute a limitation of the electronic device and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components.
The invention also proposes a computer-readable storage medium on which a computer program is stored. The computer-readable storage medium may be the Memory 20 in the electronic apparatus in fig. 3, and may also be at least one of a ROM (Read-Only Memory)/RAM (Random Access Memory), a magnetic disk, and an optical disk, and the computer-readable storage medium includes instructions for enabling a terminal device (which may be a television, an automobile, a mobile phone, a computer, a server, a terminal, or a network device) having a processor to execute the method according to the embodiments of the present invention.
In the present invention, the terms "first", "second", "third", "fourth" and "fifth" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance, and those skilled in the art can understand the specific meanings of the above terms in the present invention according to specific situations.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Although the embodiment of the present invention has been shown and described, the scope of the present invention is not limited thereto, it should be understood that the above embodiment is illustrative, and not restrictive, and that those skilled in the art can make changes, modifications and substitutions to the above embodiment within the scope of the present invention, and that these changes, modifications and substitutions are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (8)
1. A battery state of health prediction method, the method comprising:
acquiring observation data of a current battery, and acquiring a plurality of battery state tracks from a battery database, wherein the battery state tracks represent tracks of the change of the state of health of the battery along with time;
generating a state prediction track of the current battery based on the observation data and a plurality of battery state tracks;
predicting the health state of the current battery through the observation data and the state prediction track;
the step of generating a state prediction trajectory of the current battery based on the observation data and the plurality of battery state trajectories comprises:
Obtaining correlation parameters between the observation data and each battery state track;
generating a state prediction track of the current battery through a plurality of battery state tracks and the corresponding correlation parameters;
the observation data comprises the service time of the current battery, and the state prediction track reflects the change of the health state of the battery based on the service time; the step of predicting the state of health of the current battery through the observation data and the state prediction track comprises:
substituting the using time into the state prediction track to obtain a track health state corresponding to the using time in the state prediction track;
taking the trajectory state of health as the predicted state of health of the current battery.
2. The battery state of health prediction method of claim 1, wherein the step of obtaining correlation parameters between the observed data and each of the battery state trajectories comprises:
acquiring a trained correlation model, and taking the observation data and the battery state tracks as the input of the trained correlation model;
And operating the trained correlation model to obtain correlation parameters between the observation data and each battery state track.
3. The battery state of health prediction method of claim 2, wherein the step of obtaining a trained correlation model is preceded by:
establishing a relation model expressed by a mean function and a covariance function of Gaussian distribution based on the observation data and the battery state track;
obtaining model parameters, wherein the model parameters comprise hyper-parameters of a mean function and hyper-parameters of a covariance function;
establishing an initial correlation model based on the relationship model and the model parameters;
and training the initial correlation model to obtain a trained correlation model.
4. The battery state of health prediction method of claim 3, wherein the step of training the initial correlation model to obtain a trained correlation model comprises:
the mean function and the unknown parameters of the covariance function are estimated by a negative log-edge likelihood function in a maximization equation.
5. The battery state of health prediction method of claim 1, wherein the step of obtaining a plurality of battery state trajectories from a battery database is followed by:
Performing dynamic time warping on each battery state track to enable the lengths of the battery state tracks to be consistent;
adjusting the sample point in each of the battery state trajectories to a ratio of an actual capacity to a rated capacity.
6. A battery state-of-health predicting apparatus, characterized by comprising:
the battery state tracking system comprises a first acquisition module, a second acquisition module and a monitoring module, wherein the first acquisition module is used for acquiring observation data of a current battery and acquiring a plurality of battery state tracks from a battery database, and the battery state tracks represent tracks of the change of the state of health of the battery along with time;
a first generation module, configured to generate a state prediction track of the current battery based on the observation data and a plurality of battery state tracks;
the first execution module is used for predicting the health state of the current battery through the observation data and the state prediction track;
the first generation module comprises:
the first acquisition submodule is used for acquiring correlation parameters between the observation data and the battery state tracks;
the first generation submodule is used for generating a state prediction track of the current battery through a plurality of battery state tracks and the corresponding correlation parameters;
The observation data comprises the service time of the current battery, and the state prediction track reflects the change of the health state of the battery based on the service time; the first execution module comprises:
the first execution submodule is used for substituting the use time into the state prediction track to obtain a track health state corresponding to the use time in the state prediction track;
a second execution submodule configured to use the trajectory health status as a predicted health status of the current battery.
7. An electronic device, characterized in that the electronic device comprises a memory, a processor and a computer program stored on the memory and executable on the processor, which computer program, when executed by the processor, carries out the steps of the battery state of health prediction method according to any one of claims 1 to 5.
8. A computer-readable storage medium, having stored thereon a computer program which, when being executed by a processor, carries out the steps of the battery state of health prediction method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210262758.7A CN114355224B (en) | 2022-03-17 | 2022-03-17 | Battery health state prediction method and device, electronic device and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210262758.7A CN114355224B (en) | 2022-03-17 | 2022-03-17 | Battery health state prediction method and device, electronic device and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114355224A CN114355224A (en) | 2022-04-15 |
| CN114355224B true CN114355224B (en) | 2022-06-28 |
Family
ID=81094662
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210262758.7A Active CN114355224B (en) | 2022-03-17 | 2022-03-17 | Battery health state prediction method and device, electronic device and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114355224B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102445663A (en) * | 2011-09-28 | 2012-05-09 | 哈尔滨工业大学 | Method for estimating battery health of electric automobile |
| CN103675692A (en) * | 2012-09-26 | 2014-03-26 | 财团法人车辆研究测试中心 | Battery state-of-health detecting method and device |
| CN103675702A (en) * | 2013-12-04 | 2014-03-26 | 清华大学 | Method for evaluating state of health battery in real time |
| CN103728570A (en) * | 2014-01-15 | 2014-04-16 | 国家电网公司 | Battery-thermal-characteristic-based health state detection method |
Family Cites Families (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102798823A (en) * | 2012-06-15 | 2012-11-28 | 哈尔滨工业大学 | Gaussian process regression-based method for predicting state of health (SOH) of lithium batteries |
| TWI448713B (en) * | 2012-09-21 | 2014-08-11 | Method and apparatus for detecting health status of battery | |
| CN103344920B (en) * | 2013-07-01 | 2016-05-25 | 华为技术有限公司 | A kind of method and apparatus that detects cell health state |
| JP6245692B2 (en) * | 2013-11-13 | 2017-12-13 | 学校法人東海大学 | Battery state determination device and battery state determination method |
| CN104502855B (en) * | 2014-12-23 | 2017-06-13 | 广东电网有限责任公司电力科学研究院 | Lead-acid accumulator SOH detection methods and system |
| CN106125004A (en) * | 2016-08-29 | 2016-11-16 | 哈尔滨理工大学 | Lithium battery health status Forecasting Methodology based on neutral net kernel function GPR |
| CN106446520A (en) * | 2016-08-31 | 2017-02-22 | 深圳市沃特玛电池有限公司 | Estimation method for state of health (SOH) of battery |
| GB2556076B (en) * | 2016-11-17 | 2022-02-23 | Bboxx Ltd | Method |
| CN107843845A (en) * | 2017-10-23 | 2018-03-27 | 合肥国轩高科动力能源有限公司 | A kind of power lithium-ion battery SOH estimation on line methods |
| CN108169680A (en) * | 2017-12-08 | 2018-06-15 | 北京普莱德新能源电池科技有限公司 | Power battery health state evaluation method, system and electric vehicle |
| CN109061516A (en) * | 2018-10-10 | 2018-12-21 | 哈尔滨理工大学 | A kind of cell health state appraisal procedure based on fuzzy probability Comprehensive Evaluation |
| CN110133533B (en) * | 2019-06-10 | 2022-01-18 | 珠海东帆科技有限公司 | Method for estimating state of health of battery and battery management device |
| CN113189495A (en) * | 2021-04-30 | 2021-07-30 | 重庆金康新能源汽车有限公司 | Method and device for predicting health state of battery and electronic equipment |
| CN113722675A (en) * | 2021-08-25 | 2021-11-30 | 北京轻舟智航科技有限公司 | Training method of multi-modal trajectory prediction model |
| CN113434329B (en) * | 2021-08-27 | 2022-02-15 | 深圳市信润富联数字科技有限公司 | Equipment fault diagnosis and health management system |
-
2022
- 2022-03-17 CN CN202210262758.7A patent/CN114355224B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102445663A (en) * | 2011-09-28 | 2012-05-09 | 哈尔滨工业大学 | Method for estimating battery health of electric automobile |
| CN103675692A (en) * | 2012-09-26 | 2014-03-26 | 财团法人车辆研究测试中心 | Battery state-of-health detecting method and device |
| CN103675702A (en) * | 2013-12-04 | 2014-03-26 | 清华大学 | Method for evaluating state of health battery in real time |
| CN103728570A (en) * | 2014-01-15 | 2014-04-16 | 国家电网公司 | Battery-thermal-characteristic-based health state detection method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114355224A (en) | 2022-04-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Duong et al. | Heuristic Kalman optimized particle filter for remaining useful life prediction of lithium-ion battery | |
| US10387768B2 (en) | Enhanced restricted boltzmann machine with prognosibility regularization for prognostics and health assessment | |
| Kim et al. | Data-driven state of health estimation of li-ion batteries with RPT-reduced experimental data | |
| US11694011B2 (en) | Circuit health state prediction method and system based on integrated deep neural network | |
| Cui et al. | A dynamic spatial-temporal attention-based GRU model with healthy features for state-of-health estimation of lithium-ion batteries | |
| Beintema et al. | Nonlinear state-space identification using deep encoder networks | |
| Feng et al. | SOH and RUL prediction of Li-ion batteries based on improved Gaussian process regression | |
| Vidal et al. | Estimating battery state of charge using recurrent and non-recurrent neural networks | |
| Zhou et al. | Battery health prognosis using improved temporal convolutional network modeling | |
| Luzi et al. | A novel neural networks ensemble approach for modeling electrochemical cells | |
| Qin et al. | Prognostics of remaining useful life for lithium-ion batteries based on a feature vector selection and relevance vector machine approach | |
| Feng et al. | State of health estimation of large-cycle lithium-ion batteries based on error compensation of autoregressive model | |
| CN112116138A (en) | Power system prediction state estimation method and system based on data driving | |
| Bai et al. | Prognostics of Lithium-Ion batteries using knowledge-constrained machine learning and Kalman filtering | |
| CN112230154A (en) | Lithium battery residual life prediction method | |
| CN114297036A (en) | Data processing method and device, electronic equipment and readable storage medium | |
| JP2023520970A (en) | Lithium battery SOC estimation method, apparatus, and computer-readable storage medium | |
| CN114742203A (en) | Lithium battery state prediction method, system and medium based on hybrid machine learning method | |
| Fei et al. | A deep attention-assisted and memory-augmented temporal convolutional network based model for rapid lithium-ion battery remaining useful life predictions with limited data | |
| Alsuwian et al. | A Review of Expert Hybrid and Co-Estimation Techniques for SOH and RUL Estimation in Battery Management System with Electric Vehicle Application | |
| CN114355224B (en) | Battery health state prediction method and device, electronic device and readable storage medium | |
| Kunlong et al. | SOH estimation for lithium-ion batteries: A cointegration and error correction approach | |
| CN116885711A (en) | Wind power prediction method, device, equipment and readable storage medium | |
| Mostafa | Battery total capacity estimation based on the sunflower algorithm | |
| Binelo et al. | Multi‐phase method of estimation and adaptation of parameters of electrical battery models |
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 |