CN115236519A - Lithium battery health state prediction method and device based on hidden Markov model - Google Patents
Lithium battery health state prediction method and device based on hidden Markov model Download PDFInfo
- Publication number
- CN115236519A CN115236519A CN202210795342.1A CN202210795342A CN115236519A CN 115236519 A CN115236519 A CN 115236519A CN 202210795342 A CN202210795342 A CN 202210795342A CN 115236519 A CN115236519 A CN 115236519A
- Authority
- CN
- China
- Prior art keywords
- capacity
- value
- hidden markov
- estimation
- soh
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/367—Software therefor, e.g. for battery testing using modelling or look-up tables
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/392—Determining battery ageing or deterioration, e.g. state of health
Abstract
The invention discloses a method and a device for predicting the health state of a lithium battery based on a hidden Markov model, which relate to the field of lithium battery state prediction, and are characterized in that a battery capacity increment curve, an average temperature-time curve and a maximum capacity change curve are obtained by acquiring the voltage, the charging and discharging time, and the maximum capacity and the temperature of each cycle of the lithium battery, and extreme points, slopes and mean values of each curve are taken as characteristic data; calculating a correlation coefficient between the feature data and the SOH actual value, and selecting an optimal feature combination based on the correlation coefficient; and establishing and training a capacity estimation model, wherein the capacity estimation model adopts a hidden Markov model, inputting the feature difference value of the optimal feature combination into the trained capacity estimation model to obtain the capacity difference value of the next cycle, obtaining a capacity estimation value according to the current capacity value and the capacity difference value, and obtaining an SOH estimation value according to the capacity estimation value and SOH definition calculation, so that the problems of large state prediction calculation amount and the like of the conventional lithium battery are solved.
Description
Technical Field
The invention relates to the field of lithium battery state prediction, in particular to a lithium battery health state prediction method and device based on a hidden Markov model.
Background
Data driving is one of prediction methods for lithium battery SOH, and prediction of battery state of health is realized by characteristic study of data without depending on battery shape and electrochemical principle. The main data driving methods at present are:
(1) The support vector machine is mainly used for function fitting, a kernel function must meet Mercer conditions, calculation burden is caused along with increase of data quantity, and a penalty coefficient cannot be determined.
(2) The artificial neural network can independently organize and learn by simulating a human body neuron network information processing mode through a mathematical model, but the problems of high algorithm complexity and complex network structure exist in the operation process.
(3) Gaussian regression: the test data is trained, prior distribution is limited, posterior distribution is estimated, uncertainty expression of a prediction result is obtained, and the problems exist in large calculation amount and sensitive over-parameter values.
Disclosure of Invention
The technical problems mentioned in the background above are addressed. An embodiment of the present application aims to provide a method and an apparatus for predicting a health status of a lithium battery based on a hidden markov model, so as to solve the technical problems mentioned in the above background.
In a first aspect, an embodiment of the present application provides a method for predicting a health state of a lithium battery based on a hidden markov model, including the following steps:
s1, acquiring voltage, charging and discharging time, maximum capacity and temperature of each cycle of a lithium battery, acquiring a battery capacity increment curve, an average temperature-time curve and a maximum capacity change curve according to the voltage, the charging and discharging time, the maximum capacity and the temperature of each cycle, and taking an extreme point, a slope and an average value of each curve as characteristic data;
s2, calculating a correlation coefficient between the feature data and the SOH actual value, and selecting an optimal feature combination based on the correlation coefficient;
s3, establishing a capacity estimation model, wherein the capacity estimation model adopts a hidden Markov model, and training the capacity estimation model by using training data;
and S4, inputting the feature difference value of the optimal feature combination into the trained capacity estimation model to obtain the capacity difference value of the next cycle, obtaining a capacity estimation value according to the current capacity value and the capacity difference value, and calculating to obtain an SOH estimation value according to the capacity estimation value and the SOH definition.
Preferably, step S1 specifically includes:
the abscissa of the battery capacity increment curve is voltage, the ordinate is IC, and the calculation formula of IC is as follows:
wherein Q is the battery charging capacity, V is the battery voltage, and Delta Q is the battery charging capacity variation within a cell; Δ V is the variation of the battery voltage in the interval;
the abscissa of the average temperature-time curve is time, the ordinate is average temperature, and the calculation formula of the average temperature is as follows:
wherein, tk is the temperature measured at the kth time in the current cycle;
the slope formula on the right side of the peak value of the battery capacity increment curve:
juqueshi, Y 1 Is the IC value, Y, of the peak position 2 IC value after 200 cycles of peak period backward 1 Is the X-axis value, X, of the peak position 2 The value of the x axis after the peak value cycle is backwards circulated for 200 cycles;
the abscissa of the maximum capacity variation curve is the cycle number, and the ordinate is the maximum capacity value of the current cycle.
Preferably, step S2 specifically includes:
calculating each feature by Pearson correlation analysisCorrelation coefficient r between data and actual value of SOH i ：
Wherein x is i For the ith feature data extracted, n is the number of features, y i The SOH actual value corresponding to each characteristic data is calculated according to the capacity actual value,
and
is x i (i =1,2, \8230;, n) and y i (i =1,2, \8230;, n) is calculated;
the lithium battery state of health SOH is defined using the following SOH formula:
wherein Q current Is the current capacity value, Q initial Is the maximum capacity value in the current cycle;
and selecting the optimal characteristic combination by adopting a filtering method.
Preferably, the optimum characteristic combination includes peak data of the battery capacity increase curve, a slope on the right of the peak of the battery capacity increase curve, and an average temperature.
Preferably, the steps S2 and S3 further include: and repeating the steps S1-S2 in the charging and discharging cycle data of the lithium battery, and establishing training data formed by the difference between the optimal characteristic combination of each cycle and the corresponding capacity value and the optimal characteristic combination and the capacity value of the previous cycle.
Preferably, step S3 specifically includes:
s31, performing normalization processing on the optimal feature combination, inputting a feature difference value of the normalized optimal feature combination and the optimal combination feature of the previous cycle into a hidden Markov model, and predicting a feature difference value and a capacity difference value of the next cycle;
s32, adding the current characteristic data and the estimation difference to obtain the characteristic data of the hidden Markov model input next time;
and S33, repeating the steps S31-S32 until the estimation cycle is finished, carrying out reverse normalization processing on the plurality of predicted capacity difference values, respectively adding the capacity difference values to the capacity value of the previous cycle to obtain a plurality of capacity values, and converting the plurality of capacity values into a plurality of SOH estimation values according to an SOH formula.
Preferably, the estimation process of the SOH estimation model includes:
s41, hidden Markov Model (HMM) is λ = (a, B, Π), (a, B, Π) is input, λ is output, where Π represents the initial probability distribution vector, a = (a =) ij ) N×N Is a state transition matrix, where a ij Describing the Slave State S of the System i Transition to State S j N represents the number of states included in the model, and B represents a probability density function of an observed value in each state;
s42, initializing the hidden Markov model by combining a Viterbi algorithm with a k-means algorithm to obtain an initial model;
s43, solving an optimal state sequence under the historical observation sequence by using a Viterbi algorithm and updating parameters of an initial model;
s44, repeating the step S43 until the model is converged or is more than the set maximum iteration times, and finally obtaining the model parameter lambda i (i =1,2,3), the hidden estimation state of the hidden markov model is divided into three states: obtaining a parameter set { lambda ] of the hidden Markov model in an ascending state, a descending state and a stable state 1 、λ 2 、λ 3 }；
Extracting a state sequence O from the current monitoring data of the hidden Markov model, and judging the state classification of the hidden Markov model according to a maximum similarity criterion:
s i ＝arg maxP(o|λ i )，i∈{1，2，3]；
and finally, adding the capacity difference value predicted by the next state by using the current capacity value to obtain a capacity estimation value:
C i+1 ＝C i +HMM(S i )；
and S45, converting the capacity estimation value into an SOH estimation value by adopting an SOH formula.
In a second aspect, an embodiment of the present application provides a hidden markov model-based lithium battery health status prediction apparatus, including:
the characteristic acquisition module is configured to acquire the voltage, the charging and discharging time, the maximum capacity and the temperature of each cycle of the lithium battery, obtain a battery capacity increment curve, an average temperature time curve and a maximum capacity change curve according to the voltage, the charging and discharging time, the maximum capacity and the temperature of each cycle, and take an extreme point, a slope and an average value of each curve as characteristic data;
a correlation selection module configured to calculate a correlation coefficient between the feature data and an actual value of SOH, select an optimal feature combination based on the correlation coefficient;
a model training module configured to build a capacity estimation model that employs a hidden Markov model, the capacity estimation model being trained using training data;
and the estimation module is configured to input the feature difference value of the optimal feature combination into a trained capacity estimation model to obtain a capacity difference value of the next cycle, obtain a capacity estimation value according to the current capacity value and the capacity difference value, and calculate to obtain an SOH estimation value according to the capacity estimation value and an SOH definition.
In a third aspect, embodiments of the present application provide an electronic device comprising one or more processors; storage means for storing one or more programs which, when executed by one or more processors, cause the one or more processors to carry out a method as described in any one of the implementations of the first aspect.
In a fourth aspect, embodiments of the present application provide a computer-readable storage medium on which a computer program is stored, which, when executed by a processor, implements the method as described in any of the implementations of the first aspect.
Compared with the prior art, the invention has the following beneficial effects:
(1) The lithium battery health state prediction method based on the hidden Markov model solves the problems of high information redundancy, large calculated amount and the like in the data analysis process, can quickly predict the capacity fading track by using a small amount of data characteristics, and quickly predicts to obtain the SOH estimated value.
(2) The lithium battery health state prediction method based on the hidden Markov model has the advantages of good prediction effect of dynamic fluctuation and strong robustness.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is an exemplary device architecture diagram in which one embodiment of the present application may be applied;
fig. 2 is a schematic flow chart of a method for predicting the state of health of a lithium battery based on a hidden markov model according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a lithium battery health status prediction device based on hidden Markov model according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a computer device suitable for implementing an electronic apparatus according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the present invention will be described in further detail with reference to the accompanying drawings, and it is apparent that the described embodiments are only a part of the embodiments of the present invention, not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.
Fig. 1 illustrates an exemplary device architecture 100 to which a hidden markov model-based lithium battery health status prediction method or a hidden markov model-based lithium battery health status prediction device according to an embodiment of the present application may be applied.
As shown in fig. 1, the apparatus architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. Network 104 is the medium used to provide communication links between terminal devices 101, 102, 103 and server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
The user may use the terminal devices 101, 102, 103 to interact with the server 105 via the network 104 to receive or send messages or the like. Various applications, such as data processing type applications, file processing type applications, etc., may be installed on the terminal apparatuses 101, 102, 103.
The terminal devices 101, 102, 103 may be hardware or software. When the terminal devices 101, 102, 103 are hardware, they may be various electronic devices including, but not limited to, smart phones, tablet computers, laptop portable computers, desktop computers, and the like. When the terminal devices 101, 102, 103 are software, they can be installed in the electronic devices listed above. It may be implemented as multiple pieces of software or software modules (e.g., software or software modules used to provide distributed services) or as a single piece of software or software module. And is not particularly limited herein.
The server 105 may be a server that provides various services, such as a background data processing server that processes files or data uploaded by the terminal devices 101, 102, 103. The background data processing server can process the acquired files or data to generate a processing result.
The method for predicting the health state of the lithium battery based on the hidden markov model according to the embodiment of the present application may be executed by the server 105 or the terminal devices 101, 102, and 103, and accordingly, the device for predicting the health state of the lithium battery based on the hidden markov model may be installed in the server 105 or the terminal devices 101, 102, and 103.
It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation. In the case where the processed data does not need to be acquired from a remote location, the apparatus architecture described above may not include a network, but only a server or a terminal device.
Fig. 2 illustrates a method for predicting a health state of a lithium battery based on a hidden markov model according to an embodiment of the present application, including the following steps:
s1, obtaining the voltage, the charging and discharging time, the maximum capacity and the temperature of each cycle of the lithium battery, obtaining a battery capacity increment curve, an average temperature-time curve and a maximum capacity change curve according to the voltage, the charging and discharging time, the maximum capacity and the temperature of each cycle, and taking an extreme point, a slope and an average value of each curve as characteristic data.
In a specific embodiment, step S1 specifically includes:
the abscissa of the battery capacity increment curve is voltage, the ordinate is IC, and the calculation formula of IC is as follows:
wherein Q is the battery charge capacity, unit: mAh, V is the battery voltage, unit: v (volt), Δ Q is the amount of change in battery charge capacity within one cell; Δ V is the variation of the battery voltage in the interval;
the abscissa of the average temperature-time curve is time, the ordinate is average temperature, and the calculation formula of the average temperature is as follows:
wherein, tk is the temperature measured at the kth time in the current cycle; the calculation formula of the average temperature is that the temperature data measured each time in the current cycle are accumulated, and finally divided by the temperature measurement times.
The slope formula on the right side of the peak value of the battery capacity increment curve:
wherein Y is 1 Ic value, Y, of peak position 2 IC value after 200 cycles of peak period backward 1 X-axis value, X, of peak position 2 The value of the x axis after the peak value cycle is backwards circulated for 200 cycles;
the abscissa of the maximum capacity change curve is the cycle count, and the ordinate is the maximum capacity of the current cycle.
And S2, calculating a correlation coefficient between the feature data and the SOH actual value, and selecting the optimal feature combination based on the correlation coefficient.
In a specific embodiment, step S2 specifically includes:
calculating a correlation coefficient r between each characteristic data and an SOH actual value by using a Pearson correlation analysis method i ：
Wherein x is i For the extracted i-th feature data, n is the number of features, y i The SOH actual value corresponding to each characteristic data is calculated according to the capacity actual value,
and
is x i (i =1,2, \8230;, n) and y i (i =1,2, \8230;, n) is calculated;
the lithium battery state of health SOH is defined using the following SOH formula:
wherein Q is current Is the current capacity value, Q initial Is the maximum capacity value in the current cycle;
and selecting the optimal characteristic combination by adopting a filtering method.
In a particular embodiment, the optimal combination of characteristics includes peak data for the incremental battery capacity curve, the slope to the right of the peak of the incremental battery capacity curve, and the average temperature.
Specifically, the maximum capacity value in the current cycle is the initial capacity value. Coefficient of correlation r i The method is characterized in that the correlation between the capacity actual value or the corresponding SOH actual value and the characteristic data is expressed according to a correlation coefficient r i The optimal feature combination is selected by using a filtering method, and in one embodiment, the specific process is as follows: setting coefficient threshold value to be 0.8, and setting correlation coefficient r i And sequencing the features larger than 0.8 from large to small, and setting the number of the features to be selected for screening, wherein in the embodiment of the application, the number of the features is set to three, and then selecting the first three optimal features for model training, namely peak data of a battery capacity increment curve, the slope of the right side of the peak value of the battery capacity increment curve and the average temperature. In other embodiments, other suitable optimal combinations of features may be selected.
In a specific embodiment, the step S2 and the step S3 further include: and repeating the steps S1-S2 in the charging and discharging cycle data of the lithium battery, and establishing training data formed by the difference between the optimal characteristic combination of each cycle and the corresponding capacity value and the optimal characteristic combination and the capacity value of the previous cycle.
Specifically, in the first 60% of the charge-discharge cycle data of the lithium battery, the above steps are performed to obtain a training data set composed of the feature combinations with the best correlation, where the training data set is a difference data set obtained by subtracting the current capacity value corresponding to the optimal feature combination in the current cycle from the optimal feature combination and the capacity value in the previous cycle.
And S3, establishing a capacity estimation model, wherein the capacity estimation model adopts a hidden Markov model, and training the capacity estimation model by using training data.
In a specific embodiment, step S3 specifically includes:
s31, performing normalization processing on the optimal feature combination, inputting a feature difference value of the normalized optimal feature combination and the optimal combination feature of the previous cycle into a hidden Markov model, and predicting a feature difference value and a capacity difference value of the next cycle;
s32, adding the current characteristic data and the estimation difference to obtain the characteristic data of the hidden Markov model input next time;
and S33, repeating the steps S31-S32 until the estimation cycle is finished, carrying out reverse normalization processing on the plurality of predicted capacity difference values, respectively adding the capacity difference values to the capacity value of the previous cycle to obtain a plurality of capacity values, and converting the plurality of capacity values into a plurality of SOH estimation values according to an SOH formula.
Specifically, training data are divided into a training set and a verification set, the training set is used for training the hidden Markov model, the verification set is used for verifying the training effect of the hidden Markov model, MAE and RMSE are used as evaluation indexes of the hidden Markov model, after training is completed, model parameters are determined, and finally the trained hidden Markov model is obtained.
And S4, inputting the feature difference value of the optimal feature combination into the trained capacity estimation model to obtain the capacity difference value of the next cycle, obtaining a capacity estimation value according to the current capacity value and the capacity difference value, and calculating according to the capacity estimation value and the SOH definition to obtain the SOH estimation value.
In a specific embodiment, the estimation process of the SOH estimation model includes:
s41, a Hidden Markov Model (HMM) is λ = (a, B, Π), (a, B, Π) is an input, λ is an output, where Π represents an initial probability distribution vector; a = (a) ij ) N×N Is a state transition matrix, where a ij Describing the Slave State S of the System i Transition to State S j N represents the number of states included in the model, and B represents the probability density function of the observed value in each state;
s42, initializing the hidden Markov model by combining a Viterbi algorithm with a k-means algorithm to obtain an initial model;
s43, solving an optimal state sequence under the historical observation sequence by using a Viterbi algorithm and updating parameters of an initial model;
s44, repeating the step S43 until the model is converged or is more than the set maximum iteration times, and finally obtaining the model parameter lambda i (i =1,2,3), the hidden estimation state of the hidden markov model is divided into three states: obtaining a parameter set { lambda ] of the hidden Markov model in an ascending state, a descending state and a stable state 1 、λ 2 、λ 3 }；
Extracting a state sequence O from the current monitoring data of the hidden Markov model, and judging the state of the hidden Markov model according to a maximum similarity criterion:
S i ＝arg maxP(o|λ i )，i∈{1，2，3}；
and finally, adding the capacity difference value predicted by the next state by using the current capacity value to obtain a capacity estimation value:
C i+1 ＝C i +HMM(S i )；
and S45, converting the capacity estimation value into an SOH estimation value by adopting an SOH formula.
Specifically, the state sequence O corresponds to three states, i.e., an ascending state, a descending state, and a steady state.
With further reference to fig. 3, as an implementation of the methods shown in the above diagrams, the present application provides an embodiment of a lithium battery health state prediction apparatus based on hidden markov model, where the embodiment of the apparatus corresponds to the embodiment of the method shown in fig. 2, and the apparatus may be applied to various electronic devices.
The embodiment of the application provides a lithium battery health state prediction device based on a hidden Markov model, which is characterized by comprising the following steps:
the characteristic acquisition module 1 is configured to acquire the voltage, the charging and discharging time, the maximum capacity and the temperature of each cycle of the lithium battery, obtain a battery capacity increment curve, an average temperature time curve and a maximum capacity change curve according to the voltage, the charging and discharging time, the maximum capacity and the temperature of each cycle, and take an extreme point, a slope and an average value of each curve as characteristic data;
a correlation selection module 2 configured to calculate a correlation coefficient between the feature data and the SOH actual value, and select an optimal feature combination based on the correlation coefficient;
a model training module 3 configured to establish a capacity estimation model, the capacity estimation model employing a hidden markov model, the capacity estimation model being trained using training data;
and the estimation module 4 is configured to input the feature difference value of the optimal feature combination into the trained capacity estimation model to obtain a capacity difference value of the next cycle, obtain a capacity estimation value according to the current capacity value and the capacity difference value, and calculate to obtain an SOH estimation value according to the capacity estimation value and the SOH definition.
Reference is now made to fig. 4, which is a schematic diagram illustrating a computer device 400 suitable for use in implementing an electronic device (e.g., the server or the terminal device shown in fig. 1) according to an embodiment of the present application. The electronic device shown in fig. 4 is only an example, and should not bring any limitation to the functions and the use range of the embodiment of the present application.
As shown in fig. 4, the computer apparatus 400 includes a Central Processing Unit (CPU) 401 and a Graphics Processing Unit (GPU) 402, which can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 403 or a program loaded from a storage section 409 into a Random Access Memory (RAM) 404. In the RAM404, various programs and data necessary for the operation of the apparatus 400 are also stored. The CPU 401, GPU402, ROM 403, and RAM404 are connected to each other via a bus 405. An input/output (I/O) interface 406 is also connected to bus 405.
The following components are connected to the I/O interface 406: an input portion 407 including a keyboard, a mouse, and the like; an output portion 408 including a speaker and the like such as, for example, a Liquid Crystal Display (LCD); a storage portion 409 including a hard disk and the like; and a communication section 410 including a network interface card such as a LAN card, a modem, or the like. The communication section 410 performs communication processing via a network such as the internet. The driver 411 may also be connected to the I/O interface 406 as needed. A removable medium 412 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 411 as needed, so that a computer program read out therefrom is mounted into the storage section 409 as needed.
In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 410 and/or installed from the removable medium 412. The computer program performs the above-described functions defined in the method of the present application when executed by a Central Processing Unit (CPU) 401 and a Graphics Processing Unit (GPU) 402.
It should be noted that the computer readable medium described herein can be a computer readable signal medium or a computer readable medium or any combination of the two. A computer-readable medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor device, apparatus, or a combination of any of the foregoing. More specific examples of the computer readable medium may include, but are not limited to: an electrical connection having 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 portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present application, a computer readable medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution apparatus, device, or apparatus. In this application, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution apparatus, device, or apparatus. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present application may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based devices that perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The modules described in the embodiments of the present application may be implemented by software or hardware. The modules described may also be provided in a processor.
As another aspect, the present application also provides a computer-readable medium, which may be contained in the electronic device described in the above embodiments; or may be separate and not incorporated into the electronic device. The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: acquiring the voltage, the charging and discharging time and the maximum capacity and temperature of each cycle of the lithium battery, obtaining a battery capacity increment curve, an average temperature-time curve and a maximum capacity change curve according to the voltage, the charging and discharging time, the maximum capacity and the temperature of each cycle, and taking an extreme point, a slope and an average value of each curve as characteristic data; calculating a correlation coefficient between the feature data and the SOH actual value, and selecting an optimal feature combination based on the correlation coefficient; establishing a capacity estimation model, wherein the capacity estimation model adopts a hidden Markov model, and training the capacity estimation model by using training data; and inputting the characteristic difference value of the optimal characteristic combination into the trained capacity estimation model to obtain the capacity difference value of the next cycle, obtaining a capacity estimation value according to the current capacity value and the capacity difference value, and calculating according to the capacity estimation value and the SOH definition to obtain the SOH estimation value.
The above description is only a preferred embodiment of the application and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention herein disclosed is not limited to the particular combination of features described above, but also encompasses other arrangements formed by any combination of the above features or their equivalents without departing from the spirit of the invention. For example, the above features may be replaced with (but not limited to) features having similar functions disclosed in the present application.
Claims (10)
1. A lithium battery health state prediction method based on a hidden Markov model is characterized by comprising the following steps:
s1, acquiring voltage, charging and discharging time, and maximum capacity and temperature of each cycle of a lithium battery, acquiring a battery capacity increment curve, an average temperature-time curve and a maximum capacity change curve according to the voltage, the charging and discharging time, and the maximum capacity and temperature of each cycle, and taking an extreme point, a slope and an average value of each curve as characteristic data;
s2, calculating a correlation coefficient between the feature data and an SOH actual value, and selecting an optimal feature combination based on the correlation coefficient;
s3, establishing a capacity estimation model, wherein the capacity estimation model adopts a hidden Markov model and is trained by using training data;
and S4, inputting the feature difference value of the optimal feature combination into a trained capacity estimation model to obtain a capacity difference value of the next cycle, obtaining a capacity estimation value according to the current capacity value and the capacity difference value, and calculating to obtain an SOH estimation value according to the capacity estimation value and the SOH definition.
2. The method for predicting the state of health of a lithium battery based on a hidden markov model according to claim 1, wherein the step S1 specifically comprises:
the abscissa of the battery capacity increment curve is voltage, the ordinate is IC, and the calculation formula of the IC is as follows:
wherein Q is the battery charging capacity, V is the battery voltage, and Delta Q is the battery charging capacity variation within a cell; Δ V is the variation of the battery voltage in the interval;
the abscissa of the average temperature-time curve is time, the ordinate is average temperature, and the calculation formula of the average temperature is as follows:
wherein, T k Is the temperature measured at the kth time in the current cycle;
the slope formula on the right side of the peak value of the battery capacity increment curve is as follows:
wherein Y is 1 Is the IC value, Y, of the peak position 2 IC value after 200 cycles backward for peak period, x 1 X-axis value, X, of peak position 2 The value of the x axis after the peak value cycle is backwards circulated for 200 cycles;
the abscissa of the maximum capacity change curve is the cycle number, and the ordinate is the maximum capacity value of the current cycle.
3. The hidden markov model based lithium battery health status prediction method according to claim 1, wherein the step S2 specifically comprises:
calculating a correlation coefficient r between each characteristic data and an SOH actual value by using a Pearson correlation analysis method i ：
Wherein x is i For the extracted i-th feature data, n is the number of features, y i For the actual value of SOH corresponding to each characteristic data, the SOThe H actual value is calculated from the capacity actual value,
and
is x i (i =1,2, \8230;, n) and y i (i =1,2, \8230;, n) is calculated;
the lithium battery state of health SOH is defined using the following SOH formula:
wherein Q is current Is the current capacity value, Q initial Is the maximum capacity value in the current cycle;
and selecting the optimal characteristic combination by adopting a filtering method.
4. The hidden markov model-based lithium battery state of health prediction method of claim 1, wherein the optimal combination of characteristics comprises peak data of a battery capacity delta curve, a slope of a right side of a peak of the battery capacity delta curve, and an average temperature.
5. The method for predicting the health status of a lithium battery based on hidden markov models according to claim 1, wherein between the steps S2 and S3 further comprising: and repeating the steps S1-S2 in the charging and discharging cycle data of the lithium battery, and establishing training data formed by the difference between the optimal characteristic combination of each cycle and the corresponding capacity value and the optimal characteristic combination and the capacity value of the previous cycle.
6. The hidden markov model-based lithium battery health status prediction method according to claim 1, wherein the step S3 specifically comprises:
s31, performing normalization processing on the optimal feature combination, inputting a feature difference value of the normalized optimal feature combination and the optimal combination feature of the previous cycle into a hidden Markov model, and predicting a feature difference value and a capacity difference value of the next cycle;
s32, adding the current characteristic data and the estimation difference to obtain the characteristic data of the hidden Markov model input next time;
and S33, repeating the steps S31-S32 until the estimation cycle is finished, performing inverse normalization processing on the plurality of predicted capacity difference values, respectively adding the capacity difference values to the capacity value of the previous cycle to obtain a plurality of capacity values, and converting the plurality of capacity values into a plurality of SOH estimation values according to an SOH formula.
7. The hidden markov model-based lithium battery state of health prediction method of claim 1, wherein the SOH estimation model estimation process comprises:
s41, the Hidden Markov Model (HMM) is λ = (A, B, Π), (A, B, Π) is an input, λ is an output, wherein Π represents an initial probability distribution vector, A = (a =) ij ) N×N Is a state transition matrix, where a ij Describing the Slave State S of the System i Transition to State S j N represents the number of states included in the model, and B represents the probability density function of the observed value in each state;
s42, initializing the hidden Markov model by combining a Viterbi algorithm with a k-means algorithm to obtain an initial model;
s43, solving an optimal state sequence under a historical observation sequence by using a Viterbi algorithm and updating parameters of the initial model;
s44, repeating the step S43 until the model is converged or is more than the set maximum iteration times, and finally obtaining the model parameters
The hidden estimation state of the hidden markov model is divided into three states: obtaining a parameter set { lambda ] of the hidden Markov model in an ascending state, a descending state and a stable state 1 、λ 2 、λ 3 }；
Extracting a state sequence O from the current monitoring data of the hidden Markov model, and judging the state classification of the hidden Markov model according to a maximum similarity criterion:
S i ＝arg max P(o|λ i )，i∈{1，2，3}；
and finally, adding the capacity difference value predicted by the next state by using the current capacity value to obtain a capacity estimation value:
C i+1 ＝C i +HMM(S i )；
and S45, converting the capacity estimation value into an SOH estimation value by adopting an SOH formula.
8. A lithium battery health state prediction device based on a hidden Markov model is characterized by comprising:
the characteristic acquisition module is configured to acquire the voltage, the charging and discharging time, the maximum capacity and the temperature of each cycle of the lithium battery, obtain a battery capacity increment curve, an average temperature time curve and a maximum capacity change curve according to the voltage, the charging and discharging time, the maximum capacity and the temperature of each cycle, and take extreme points, slopes and average values of each curve as characteristic data;
a correlation selection module configured to calculate a correlation coefficient between the feature data and an actual value of SOH, select an optimal feature combination based on the correlation coefficient;
a model training module configured to build a capacity estimation model that employs a hidden Markov model, the capacity estimation model being trained using training data;
and the estimation module is configured to input the feature difference value of the optimal feature combination into a trained capacity estimation model to obtain a capacity difference value of the next cycle, obtain a capacity estimation value according to the current capacity value and the capacity difference value, and calculate to obtain an SOH estimation value according to the capacity estimation value and an SOH definition.
9. An electronic device, comprising:
one or more processors;
a storage device for storing one or more programs,
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method recited in any of claims 1-7.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210795342.1A CN115236519A (en) | 2022-07-07 | 2022-07-07 | Lithium battery health state prediction method and device based on hidden Markov model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210795342.1A CN115236519A (en) | 2022-07-07 | 2022-07-07 | Lithium battery health state prediction method and device based on hidden Markov model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115236519A true CN115236519A (en) | 2022-10-25 |
Family
ID=83671483
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210795342.1A Pending CN115236519A (en) | 2022-07-07 | 2022-07-07 | Lithium battery health state prediction method and device based on hidden Markov model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115236519A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115856646A (en) * | 2023-03-03 | 2023-03-28 | 中山大学 | Lithium ion battery early life prediction method based on three-dimensional voltage characteristics |
| CN116011998A (en) * | 2023-03-23 | 2023-04-25 | 深圳市杰成镍钴新能源科技有限公司 | Retired battery recycling and classifying treatment method and device |
| CN116298906A (en) * | 2023-01-19 | 2023-06-23 | 四川新能源汽车创新中心有限公司 | Battery capacity prediction model training method, prediction method, device and medium |
| CN116299015A (en) * | 2023-05-25 | 2023-06-23 | 广汽埃安新能源汽车股份有限公司 | Battery state evaluation method, battery state evaluation device, electronic equipment and storage medium |
| CN116449209A (en) * | 2023-01-12 | 2023-07-18 | 帕诺(常熟)新能源科技有限公司 | Actual operation energy storage lithium capacitance prediction method based on LSTM |
-
2022
- 2022-07-07 CN CN202210795342.1A patent/CN115236519A/en active Pending
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116449209A (en) * | 2023-01-12 | 2023-07-18 | 帕诺(常熟)新能源科技有限公司 | Actual operation energy storage lithium capacitance prediction method based on LSTM |
| CN116298906A (en) * | 2023-01-19 | 2023-06-23 | 四川新能源汽车创新中心有限公司 | Battery capacity prediction model training method, prediction method, device and medium |
| CN116298906B (en) * | 2023-01-19 | 2024-04-16 | 四川新能源汽车创新中心有限公司 | Battery capacity prediction model training method, prediction method, device and medium |
| CN115856646A (en) * | 2023-03-03 | 2023-03-28 | 中山大学 | Lithium ion battery early life prediction method based on three-dimensional voltage characteristics |
| CN115856646B (en) * | 2023-03-03 | 2023-05-23 | 中山大学 | Lithium ion battery early life prediction method based on three-dimensional voltage characteristics |
| CN116011998A (en) * | 2023-03-23 | 2023-04-25 | 深圳市杰成镍钴新能源科技有限公司 | Retired battery recycling and classifying treatment method and device |
| CN116011998B (en) * | 2023-03-23 | 2023-06-30 | 深圳市杰成镍钴新能源科技有限公司 | Retired battery recycling and classifying treatment method and device |
| CN116299015A (en) * | 2023-05-25 | 2023-06-23 | 广汽埃安新能源汽车股份有限公司 | Battery state evaluation method, battery state evaluation device, electronic equipment and storage medium |
| CN116299015B (en) * | 2023-05-25 | 2023-08-08 | 广汽埃安新能源汽车股份有限公司 | Battery state evaluation method, battery state evaluation device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Liu et al. | A data-driven approach with uncertainty quantification for predicting future capacities and remaining useful life of lithium-ion battery | |
| CN115236519A (en) | Lithium battery health state prediction method and device based on hidden Markov model | |
| Li et al. | Lithium-ion battery capacity estimation—A pruned convolutional neural network approach assisted with transfer learning | |
| Bian et al. | State-of-charge sequence estimation of lithium-ion battery based on bidirectional long short-term memory encoder-decoder architecture | |
| CN110824364A (en) | Lithium battery SOH estimation and RUL prediction method based on AST-LSTM neural network | |
| Du et al. | Data-driven estimation of remaining useful lifetime and state of charge for lithium-ion battery | |
| Cui et al. | A dynamic spatial-temporal attention-based GRU model with healthy features for state-of-health estimation of lithium-ion batteries | |
| Zhou et al. | Prognostics for state of health of lithium-ion batteries based on Gaussian process regression | |
| Lyu et al. | Li-ion battery prognostic and health management through an indirect hybrid model | |
| Huang et al. | A comprehensively optimized lithium-ion battery state-of-health estimator based on Local Coulomb Counting Curve | |
| CN113219357A (en) | Battery pack health state calculation method and system and electronic equipment | |
| Wu et al. | Attention-based encoder-decoder networks for state of charge estimation of lithium-ion battery | |
| Biggio et al. | Dynaformer: A deep learning model for ageing-aware battery discharge prediction | |
| CN116298936A (en) | Intelligent lithium ion battery health state prediction method in incomplete voltage range | |
| How et al. | SOC estimation using deep bidirectional gated recurrent units with tree parzen estimator hyperparameter optimization | |
| Wang et al. | Fast modeling of the capacity degradation of lithium-ion batteries via a conditional temporal convolutional encoder–decoder | |
| Cao et al. | A flexible battery capacity estimation method based on partial voltage curves and polynomial fitting | |
| Schmitt et al. | State-of-health estimation by virtual experiments using recurrent decoder–encoder based lithium-ion digital battery twins trained on unstructured battery data | |
| Bak et al. | Accurate estimation of battery SOH and RUL based on a progressive lstm with a time compensated entropy index | |
| Mazzi et al. | Lithium-ion battery state of health estimation using a hybrid model based on a convolutional neural network and bidirectional gated recurrent unit | |
| Anandhakumar et al. | Extreme learning machine model with honey badger algorithm based state-of-charge estimation of lithium-ion battery | |
| Schmitt et al. | Effective estimation of battery state-of-health by virtual experiments via transfer-and meta-learning | |
| Wang et al. | State of Health estimation for lithium-ion batteries using Random Forest and Gated Recurrent Unit | |
| CN116754949A (en) | Intelligent health state prediction method for lithium ion battery | |
| Zhang et al. | Improved LSTM based state of health estimation using random segments of the charging curves for lithium-ion batteries |
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 |