Lithium battery health status prediction method and device based on hidden Markov model

Through the Hidden Markov model, the health status of lithium batteries is predicted, and the problems of high computing complexity and high information redundancy in the existing technology are solved, and the rapid and accurate prediction of the capacity decay trajectory of lithium batteries is achieved, with strong dynamic volatility. Very good.

CN115236519BActive Publication Date: 2024-11-26QUANZHOU INST OF EQUIP MFG +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202210795342.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-07-07
Publication Date
2024-11-26
Estimated Expiration
2042-07-07

AI Technical Summary

Technical Problem

The existing lithium battery health status prediction methods have problems such as high computational complexity, high information redundancy and large calculation volume, and it is difficult to quickly and effectively predict the capacity decay trajectory.

Method used

Using the lithium battery health status prediction method based on the Hidden Markov model, the correlation coefficient is calculated by obtaining voltage, charge and discharge time and temperature data, selecting the best feature combination, establishing a capacity estimation model, and using the Hidden Markov model for training And prediction, dynamic volatility is better and robust.

Benefits of technology

It quickly predicts the capacity decay trajectory of lithium battery, reduces information redundancy and calculation amount, has good dynamic fluctuation prediction effect, strong robustness, and can quickly obtain SOH estimation.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115236519B_ABST
    Figure CN115236519B_ABST
Patent Text Reader

Abstract

The invention discloses a lithium battery health state prediction method and device based on a hidden Markov model, which relates to the field of lithium battery state prediction. By acquiring the voltage, charge and discharge time, maximum capacity and temperature of each cycle of the lithium battery, a battery capacity increment curve, an average temperature time curve and a maximum capacity change curve are obtained, and the extreme point, slope and mean of each curve are used as feature data; the correlation coefficient between the feature data and the actual SOH value is calculated, and the best feature combination is selected based on the correlation coefficient; a capacity estimation model is established and trained, the capacity estimation model adopts the hidden Markov model, the feature difference of the best feature combination is input into the trained capacity estimation model, the capacity difference of the next cycle is obtained, the capacity estimation value is obtained according to the current capacity value and the capacity difference, and the SOH estimation value is calculated according to the capacity estimation value and the SOH definition, so as to solve the problem of large calculation amount in the existing lithium battery state prediction.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of lithium battery state prediction, and in particular to a lithium battery health state prediction method and device based on a hidden Markov model. Background Art

[0002] Data-driven is one of the methods for predicting lithium battery SOH. It is independent of battery shape and electrochemical principles and can predict the battery health status by studying the characteristics of data. The main data-driven methods are:

[0003] (1) Support vector machine: The focus is on function fitting. The kernel function must satisfy the Mercer condition. However, as the amount of data increases, it will cause a computational burden and it will be impossible to determine the penalty coefficient.

[0004] (2) Artificial neural networks simulate the way human neural networks process information through mathematical models and are able to organize and learn autonomously. However, there are problems with the high complexity of algorithms and complex network structures during the operation process.

[0005] (3) Gaussian regression: Train the test data, restrict the prior distribution, estimate the posterior distribution, and obtain the uncertainty expression of the prediction results. The problems are large amount of calculation and sensitivity to hyperparameter values. Summary of the invention

[0006] In view of the technical problems mentioned in the above background technology, the purpose of the embodiments of the present application is to propose a method and device for predicting the health status of a lithium battery based on a hidden Markov model to solve the technical problems mentioned in the above background technology section.

[0007] In a first aspect, an embodiment of the present application provides a method for predicting the health status of a lithium battery based on a hidden Markov model, comprising the following steps:

[0008] S1, obtaining the voltage, charge and discharge time, maximum capacity of each cycle and temperature of the lithium battery, and obtaining the battery capacity increment curve, average temperature time curve and maximum capacity change curve according to the voltage, charge and discharge time, maximum capacity of each cycle and temperature, and taking the extreme point, slope and mean value of each curve as characteristic data;

[0009] S2, calculate the correlation coefficient between the feature data and the actual value of SOH, and select the best feature combination based on the correlation coefficient;

[0010] S3, establishing a capacity estimation model, the capacity estimation model adopts a hidden Markov model, and uses the training data to train the capacity estimation model;

[0011] S4, input the feature difference of the best feature combination into the trained capacity estimation model to obtain the capacity difference of the next cycle, obtain the capacity estimation value according to the current capacity value and the capacity difference, and obtain the SOH estimation value according to the capacity estimation value and the SOH definition.

[0012] Preferably, step S1 specifically includes:

[0013] The horizontal axis of the battery capacity increment curve is voltage, and the vertical axis is IC. The calculation formula of IC is as follows:

[0014]

[0015] Where Q is the battery charging capacity, V is the battery voltage, ΔQ is the change in battery charging capacity within a small interval; ΔV is the change in battery voltage within the interval;

[0016] The horizontal axis of the average temperature time curve is time, and the vertical axis is the average temperature. The calculation formula of the average temperature is as follows:

[0017]

[0018] Where Tk is the temperature measured for the kth time in the current cycle;

[0019] The formula for the slope of the right side of the peak of the battery capacity increment curve is:

[0020]

[0021] In the figure, Y1 is the IC value at the peak position, Y2 is the IC value after 200 cycles from the peak period, x1 is the X-axis value at the peak position, and x2 is the X-axis value after 200 cycles from the peak period;

[0022] The horizontal axis of the maximum capacity change curve is the number of cycles, and the vertical axis is the maximum capacity value of the current cycle.

[0023] Preferably, step S2 specifically includes:

[0024] The Pearson correlation analysis method was used to calculate the correlation coefficient r between each characteristic data and the actual value of SOH i :

[0025]

[0026] Among them, x i is the i-th feature data extracted, n is the number of features, y i is the actual SOH value corresponding to each characteristic data, which is calculated based on the actual capacity value. and For x i(i=1,2,…,n) and y i The mean of (i=1, 2, ..., n);

[0027] The following SOH formula is used to define the lithium battery health state SOH:

[0028]

[0029] Among them, Q current is the current capacity value, Q initial is the maximum capacity value in the current cycle;

[0030] The best feature combination is selected using filtering method.

[0031] Preferably, the best feature combination includes the peak data of the battery capacity increment curve, the right slope of the peak of the battery capacity increment curve, and the average temperature.

[0032] Preferably, between steps S2 and S3, the step further includes: repeating steps S1-S2 in the charge and discharge cycle data of the lithium battery to establish training data consisting of the best feature combination and its corresponding capacity value of each cycle and the difference between the best feature combination and capacity value of the previous cycle.

[0033] Preferably, step S3 specifically includes:

[0034] S31, normalizing the best feature combination, and inputting the feature difference between the best feature combination after normalization and the best combination feature of the previous cycle into a hidden Markov model to predict the feature difference and capacity difference of the next cycle;

[0035] S32, adding the current feature data to the estimated difference to obtain feature data to be input into the hidden Markov model next time;

[0036] S33, repeating steps S31-S32 until the estimation cycle ends, performing denormalization processing on the predicted multiple capacity difference values ​​and adding them to the capacity value of the previous cycle respectively to obtain multiple capacity values, and converting the multiple capacity values ​​into multiple SOH estimation values ​​according to the SOH formula.

[0037] Preferably, the estimation process of the SOH estimation model includes:

[0038] 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 the state transfer matrix, where a ij Describe the system from state S i Transfer to state S jThe probability of, N represents the number of states contained in the model, B represents the probability density function of the observed value in each state;

[0039] S42, using the Viterbi algorithm combined with the k-means algorithm to initialize the hidden Markov model to obtain an initial model;

[0040] S43, using the Viterbi algorithm to find the optimal state sequence under the historical observation sequence and update the parameters of the initial model;

[0041] S44, repeat step S43 until the model converges or exceeds the set maximum number of iterations, and the final model parameter λ i The output of (i=1, 2, 3), the hidden estimated state of the hidden Markov model is divided into three states: rising state, falling state, and stable state, and the parameter set of the hidden Markov model {λ1, λ2, λ3} is obtained;

[0042] Extract the state sequence O from the current monitoring data of the hidden Markov model, and determine the state classification to which it belongs according to the maximum similarity criterion:

[0043] s i = arg maxP(o|λ i ), i∈{1, 2, 3];

[0044] Finally, the capacity estimate is obtained by adding the current capacity value to the capacity difference predicted for the next state:

[0045] C i+1 =C i +HMM(S i );

[0046] S45, convert the capacity estimate into an SOH estimate using the SOH formula.

[0047] In a second aspect, an embodiment of the present application provides a lithium battery health status prediction device based on a hidden Markov model, comprising:

[0048] The feature acquisition module is configured to acquire the voltage, charge and discharge time, maximum capacity of each cycle and temperature of the lithium battery, obtain the battery capacity increment curve, average temperature time curve and maximum capacity change curve according to the voltage, charge and discharge time, maximum capacity of each cycle and temperature, and use the extreme point, slope and mean of each curve as feature data;

[0049] A correlation selection module is configured to calculate a correlation coefficient between the feature data and the actual value of SOH, and select an optimal feature combination based on the correlation coefficient;

[0050] A model training module is configured to establish a capacity estimation model, wherein the capacity estimation model adopts a hidden Markov model and uses training data to train the capacity estimation model;

[0051] The estimation module is configured to input the feature difference of the optimal feature combination into a trained capacity estimation model to obtain the capacity difference of the next cycle, obtain a capacity estimation value based on the current capacity value and the capacity difference, and obtain an SOH estimation value based on the capacity estimation value and the SOH definition.

[0052] In a third aspect, an embodiment of the present application provides an electronic device comprising one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by one or more processors, the one or more processors implement a method as described in any implementation manner in the first aspect.

[0053] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in any implementation manner in the first aspect.

[0054] Compared with the prior art, the present invention has the following beneficial effects:

[0055] (1) The lithium battery health status prediction method based on the hidden Markov model of the present invention solves the difficulties such as high information redundancy and large amount of calculation in the data analysis process. A small amount of data features can be used to quickly predict the capacity decay trajectory and quickly predict the SOH estimate.

[0056] (2) The lithium battery health status prediction method based on the hidden Markov model of the present invention has good prediction effect on dynamic fluctuations and strong robustness. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0058] Figure 1 is an exemplary device architecture diagram to which an embodiment of the present application may be applied;

[0059] Figure 2 A schematic diagram of a flow chart of a lithium battery health status prediction method based on a hidden Markov model according to an embodiment of the present invention;

[0060] Figure 3A schematic diagram of a lithium battery health status prediction device based on a hidden Markov model according to an embodiment of the present invention;

[0061] Figure 4 It is a schematic diagram of the structure of a computer device suitable for implementing the electronic device of the embodiment of the present application. DETAILED DESCRIPTION

[0062] In order to make the purpose, technical scheme and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0063] Figure 1 An exemplary device architecture 100 is shown to which a lithium battery health state prediction method based on a hidden Markov model or a lithium battery health state prediction device based on a hidden Markov model according to an embodiment of the present application can be applied.

[0064] like Figure 1 As shown, the device architecture 100 may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0065] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various applications, such as data processing applications, file processing applications, etc., can be installed on terminal devices 101, 102, 103.

[0066] Terminal devices 101, 102, 103 can be hardware or software. When terminal devices 101, 102, 103 are hardware, they can be various electronic devices, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, etc. When terminal devices 101, 102, 103 are software, they can be installed in the electronic devices listed above. They can be implemented as multiple software or software modules (for example, software or software modules used to provide distributed services), or they can be implemented as a single software or software module. No specific limitation is made here.

[0067] 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, and 103. The background data processing server may process the acquired files or data and generate processing results.

[0068] It should be noted that the lithium battery health status prediction method based on the hidden Markov model provided in the embodiment of the present application can be executed by the server 105, or by the terminal devices 101, 102, 103. Accordingly, the lithium battery health status prediction device based on the hidden Markov model can be set in the server 105, or in the terminal devices 101, 102, 103.

[0069] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided as required. In the case where the processed data does not need to be obtained remotely, the above device architecture may not include a network, but only a server or a terminal device.

[0070] Figure 2 A method for predicting the health status of a lithium battery based on a hidden Markov model is shown in an embodiment of the present application, comprising the following steps:

[0071] S1, obtain the voltage, charge and discharge time, maximum capacity of each cycle and temperature of the lithium battery, and obtain the battery capacity increment curve, average temperature time curve and maximum capacity change curve according to the voltage, charge and discharge time, maximum capacity of each cycle and temperature, and use the extreme point, slope and mean of each curve as characteristic data.

[0072] In a specific embodiment, step S1 specifically includes:

[0073] The horizontal axis of the battery capacity increment curve is voltage, and the vertical axis is IC. The calculation formula of IC is as follows:

[0074]

[0075] Wherein, Q is the battery charging capacity, unit: mAh, V is the battery voltage, unit: V (volt), ΔQ is the change of battery charging capacity within a small interval; ΔV is the change of battery voltage within the interval;

[0076] The horizontal axis of the average temperature time curve is time, and the vertical axis is the average temperature. The calculation formula of the average temperature is as follows:

[0077]

[0078] Wherein, Tk is the temperature measured for the kth time in the current cycle; the calculation formula of the average temperature is to accumulate the temperature data measured each time in the current cycle and finally divide it by the number of temperature measurements.

[0079] The formula for the slope of the right side of the peak of the battery capacity increment curve is:

[0080]

[0081] Among them, Y1 is the Ic value at the peak position, Y2 is the IC value after 200 cycles of the peak period, x1 is the X-axis value of the peak position, and x2 is the X-axis value after 200 cycles of the peak period;

[0082] The horizontal axis of the maximum capacity change curve is the number of cycles, and the vertical axis is the maximum capacity of the current cycle.

[0083] S2, calculate the correlation coefficient between the feature data and the actual value of SOH, and select the best feature combination based on the correlation coefficient.

[0084] In a specific embodiment, step S2 specifically includes:

[0085] The Pearson correlation analysis method was used to calculate the correlation coefficient r between each characteristic data and the actual value of SOH i :

[0086]

[0087] Among them, x i is the i-th feature data extracted, n is the number of features, y i is the actual SOH value corresponding to each characteristic data, which is calculated based on the actual capacity value. and For x i (i=1,2,…,n) and y i The mean of (i=1, 2, ..., n);

[0088] The following SOH formula is used to define the lithium battery health state SOH:

[0089]

[0090] Among them, Q current is the current capacity value, Q initial is the maximum capacity value in the current cycle;

[0091] The best feature combination is selected using filtering method.

[0092] In a specific embodiment, the best feature combination includes peak data of the battery capacity increment curve, the peak right slope of the battery capacity increment curve, and the average temperature.

[0093] Specifically, the maximum capacity value in the current cycle is the initial capacity value. i It represents the correlation between the actual capacity value or its corresponding SOH actual value and the characteristic data, according to the correlation coefficient r i The best feature combination is selected by filtering method. In one embodiment, the specific process is as follows: the coefficient threshold is set to 0.8, the correlation coefficient r i The features with a value greater than 0.8 are sorted from large to small, and the number of features to be selected is set for screening. In the embodiment of the present application, the number of features is set to three, and the first three optimal features are selected for model training, which are the peak data of the battery capacity increment curve, the right slope of the peak of the battery capacity increment curve, and the average temperature. In other embodiments, other suitable optimal feature combinations can also be selected.

[0094] In a specific embodiment, steps S2 and S3 also include: repeating steps S1-S2 in the charge and discharge cycle data of the lithium battery to establish training data consisting of the best feature combination and its corresponding capacity value of each cycle and the difference between the best feature combination and capacity value of the previous cycle.

[0095] Specifically, the above steps are performed on the first 60% charge and discharge cycle data of the lithium battery to obtain a training data set composed of the best correlated feature combination, which is a difference data set obtained by subtracting the optimal feature combination in the current cycle and the current capacity value corresponding to it from the optimal feature combination and capacity value of the previous cycle.

[0096] S3, establish a capacity estimation model, the capacity estimation model adopts a hidden Markov model, and uses the training data to train the capacity estimation model.

[0097] In a specific embodiment, step S3 specifically includes:

[0098] S31, normalizing the optimal feature combination, and inputting the feature difference between the normalized optimal feature combination and the optimal combination feature of the previous cycle into a hidden Markov model to predict the feature difference and capacity difference of the next cycle;

[0099] S32, adding the current feature data to the estimated difference to obtain feature data to be input into the hidden Markov model next time;

[0100] S33, repeating steps S31-S32 until the estimation cycle ends, performing denormalization processing on the predicted multiple capacity difference values ​​and adding them to the capacity value of the previous cycle respectively to obtain multiple capacity values, and converting the multiple capacity values ​​into multiple SOH estimation values ​​according to the SOH formula.

[0101] Specifically, the training data is divided into a training set and a validation set. The training set is used to train the hidden Markov model, and the validation set is used to verify the training effect of the hidden Markov model. MAE and RMSE are used as evaluation indicators of the hidden Markov model. After the training is completed, the model parameters are determined, and finally a trained hidden Markov model is obtained.

[0102] S4, input the feature difference of the best feature combination into the trained capacity estimation model to obtain the capacity difference of the next cycle, obtain the capacity estimation value according to the current capacity value and the capacity difference, and obtain the SOH estimation value according to the capacity estimation value and the SOH definition.

[0103] In a specific embodiment, the estimation process of the SOH estimation model includes:

[0104] 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 the state transfer matrix, where a ij Describe the system from state S i Transfer to state S j The probability of, N represents the number of states contained in the model, B represents the probability density function of the observed value in each state;

[0105] S42, using the Viterbi algorithm combined with the k-means algorithm to initialize the hidden Markov model to obtain an initial model;

[0106] S43, using the Viterbi algorithm to find the optimal state sequence under the historical observation sequence and update the parameters of the initial model;

[0107] S44, repeat step S43 until the model converges or exceeds the set maximum number of iterations, and the final model parameter λ i The output of (i=1, 2, 3), the hidden estimated state of the hidden Markov model is divided into three states: rising state, falling state, and stable state, and the parameter set of the hidden Markov model {λ1, λ2, λ3} is obtained;

[0108] Extract the state sequence O from the current monitoring data of the hidden Markov model and determine its state according to the maximum similarity criterion:

[0109] S i = arg maxP(o|λ i ), i∈{1, 2, 3};

[0110] Finally, the capacity estimate is obtained by adding the current capacity value to the capacity difference predicted for the next state:

[0111] C i+1 =C i +HMM(S i );

[0112] S45, convert the capacity estimate into an SOH estimate using the SOH formula.

[0113] Specifically, the state sequence O corresponds to three states: rising state, falling state, and stable state.

[0114] Further references Figure 3 As an implementation of the methods shown in the above figures, the present application provides an embodiment of a lithium battery health status prediction device based on a hidden Markov model. Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0115] The embodiment of the present application provides a lithium battery health status prediction device based on a hidden Markov model, which is characterized by comprising:

[0116] The feature acquisition module 1 is configured to acquire the voltage, charge and discharge time, maximum capacity of each cycle and temperature of the lithium battery, and obtain the battery capacity increment curve, average temperature time curve and maximum capacity change curve according to the voltage, charge and discharge time, maximum capacity of each cycle and temperature, and use the extreme point, slope and mean of each curve as feature data;

[0117] A correlation selection module 2 is configured to calculate a correlation coefficient between the feature data and the actual value of the SOH, and select an optimal feature combination based on the correlation coefficient;

[0118] A model training module 3 is configured to establish a capacity estimation model, wherein the capacity estimation model adopts a hidden Markov model and uses training data to train the capacity estimation model;

[0119] The estimation module 4 is configured to input the feature difference of the best feature combination into the trained capacity estimation model to obtain the capacity difference of the next cycle, obtain the capacity estimation value according to the current capacity value and the capacity difference, and obtain the SOH estimation value according to the capacity estimation value and the SOH definition.

[0120] Reference below Figure 4 , which shows an electronic device (eg Figure 1 A schematic diagram of the structure of a computer device 400 (a server or terminal device as shown). Figure 4 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0121] like Figure 4 As shown, the computer device 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 the program stored in the read-only memory (ROM) 403 or the program loaded from the storage part 409 to the random access memory (RAM) 404. In the RAM 404, various programs and data required for the operation of the device 400 are also stored. The CPU 401, GPU 402, ROM 403 and RAM 404 are connected to each other through a bus 405. An input / output (I / O) interface 406 is also connected to the bus 405.

[0122] The following components are connected to the I / O interface 406: an input section 407 including a keyboard, a mouse, etc.; an output section 408 including a display such as a liquid crystal display (LCD), etc. and a speaker, etc.; a storage section 409 including a hard disk, etc.; and a communication section 410 including a network interface card such as a LAN card, a modem, etc. The communication section 410 performs communication processing via a network such as the Internet. A drive 411 can 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, etc., is installed on the drive 411 as needed so that a computer program read therefrom is installed into the storage section 409 as needed.

[0123] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication part 410, and / or installed from a removable medium 412. When the computer program is executed by a central processing unit (CPU) 401 and a graphics processing unit (GPU) 402, the above-mentioned functions defined in the method of the present application are executed.

[0124] It should be noted that the computer-readable medium described in the present application may be a computer-readable signal medium or a computer-readable medium or any combination of the above two. The computer-readable medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared or semiconductor device, device or component, or any combination of the above. More specific examples of computer-readable media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, 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 disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution device, device or device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium may also be any computer-readable medium other than a computer-readable medium that can send, propagate or transmit a program for use by or in conjunction with an instruction execution device, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0125] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0126] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the devices, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based device that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0127] The modules involved in the embodiments described in this application may be implemented by software or hardware, and the modules described may also be set in a processor.

[0128] As another aspect, the present application also provides a computer-readable medium, which may be included in the electronic device described in the above embodiment; or it may exist alone and not be assembled into the electronic device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by the electronic device, the electronic device: obtains the voltage, charge and discharge time, maximum capacity of each cycle and temperature of the lithium battery, obtains the battery capacity increment curve, average temperature time curve and maximum capacity change curve according to the voltage, charge and discharge time, maximum capacity of each cycle and temperature, and takes the extreme point, slope and mean of each curve as feature data; calculates the correlation coefficient between the feature data and the actual value of SOH, and selects the best feature combination based on the correlation coefficient; establishes a capacity estimation model, the capacity estimation model adopts a hidden Markov model, and uses the training data to train the capacity estimation model; inputs the feature difference of the best feature combination into the trained capacity estimation model, obtains the capacity difference of the next cycle, obtains the capacity estimation value according to the current capacity value and the capacity difference, and calculates the SOH estimation value according to the capacity estimation value and the SOH definition.

[0129] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above invention concept. For example, the above features are replaced with the technical features with similar functions disclosed in this application (but not limited to) by each other to form a technical solution.

Claims

1. A method for predicting the health status of a lithium battery based on a hidden Markov model, characterized in that: The following steps are involved: S1, obtaining the voltage, charge and discharge time, maximum capacity of each cycle and temperature of the lithium battery, and obtaining a battery capacity increment curve, an average temperature time curve and a maximum capacity change curve according to the voltage, charge and discharge time, maximum capacity of each cycle and temperature, and taking the extreme point, slope and mean of each curve as characteristic data; S2, calculating the correlation coefficient between the feature data and the actual value of SOH, and selecting the best feature combination based on the correlation coefficient; S3, establishing a capacity estimation model, wherein the capacity estimation model adopts a hidden Markov model and uses training data to train the capacity estimation model; 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 obtaining an SOH estimation value according to the capacity estimation value and the SOH definition. The estimation process of the capacity estimation model includes: S41, the hidden Markov model is λ=(A,B,Π), (A,B,Π) is the input, λ is the output, where Π represents the initial probability distribution vector, A=(a ij ) N×N is the state transfer matrix, where a ij Describe the system from state S i Transfer to state S j The probability of, N represents the number of states contained in the model, B represents the probability density function of the observed value in each state; S42, initializing the hidden Markov model using a Viterbi algorithm combined with a k-means algorithm to obtain an initial model; S43, using the Viterbi algorithm to find the optimal state sequence under the historical observation sequence and update the parameters of the initial model; S44, repeat step S43 until the model converges or exceeds the set maximum number of iterations, and the final model parameter λ i (i=1, 2, 3) output, the hidden estimated state of the hidden Markov model is divided into three states: rising state, falling state, and stable state, and the parameter set {λ1, λ2, λ3} of the hidden Markov model is obtained; Extract the state sequence o from the current monitoring data of the hidden Markov model, and determine the state classification to which it belongs according to the maximum similarity criterion: S i =argmaxP(o|λ i ),i∈{1,2,3}; Finally, the capacity estimate is obtained by adding the current capacity value to the capacity difference predicted for the next state: C t+1 =C t +HMM(S i ); S45, convert the capacity estimate into an SOH estimate using the SOH formula.

2. The method for predicting the health status of a lithium battery based on a hidden Markov model according to claim 1, characterized in that: The step S1 specifically includes: The abscissa of the battery capacity increment curve is voltage, and the ordinate is IC. The calculation formula of IC is as follows: Where Q is the battery charging capacity, V is the battery voltage, ΔQ is the change in battery charging capacity within a small interval; ΔV is the change in battery voltage within the interval; The abscissa of the average temperature time curve is time, and the ordinate is average temperature. The calculation formula of the average temperature is as follows: Among them, T k is the temperature measured for the kth time in the current cycle; The slope formula of the right side of the peak value of the battery capacity increment curve is: Among them, Y1 is the IC value at the peak position, Y2 is the IC value after 200 cycles of the peak period, x1 is the X-axis value at the peak position, and x2 is the X-axis value after 200 cycles of the peak period; The horizontal axis of the maximum capacity variation curve is the number of cycles, and the vertical axis is the maximum capacity value of the current cycle.

3. The method for predicting the health status of a lithium battery based on a hidden Markov model according to claim 1, characterized in that: The step S2 specifically includes: The Pearson correlation analysis method was used to calculate the correlation coefficient r between each characteristic data and the actual value of SOH p : Among them, x p is the pth feature data extracted, n is the number of features, y p is the actual SOH value corresponding to each characteristic data, which is calculated based on the actual capacity value. and For x p (p=1,2,…,n) and y p The mean of (p=1,2,…,n); The following SOH formula is used to define the lithium battery health state SOH: Among them, Q current is the current capacity value, Q initial is the maximum capacity value in the current cycle; The best feature combination is selected using filtering method.

4. The method for predicting the health status of a lithium battery based on a hidden Markov model according to claim 1, characterized in that: The optimal feature combination includes peak data of the battery capacity increment curve, the peak right slope of the battery capacity increment curve, and the average temperature.

5. The method for predicting the health status of a lithium battery based on a hidden Markov model according to claim 1, characterized in that: The step between steps S2 and S3 also includes: repeating steps S1-S2 in the charge and discharge cycle data of the lithium battery to establish training data consisting of the best feature combination and its corresponding capacity value of each cycle and the difference between the best feature combination and capacity value of the previous cycle.

6. The method for predicting the health status of a lithium battery based on a hidden Markov model according to claim 1, characterized in that: The step S3 specifically includes: S31, normalizing the optimal feature combination, and inputting the feature difference between the normalized optimal feature combination and the optimal combination feature of the previous cycle into a hidden Markov model to predict the feature difference and capacity difference of the next cycle; S32, adding the current feature data to the feature difference to obtain feature data to be input into the hidden Markov model next time; S33, repeating steps S31-S32 until the estimation cycle ends, performing denormalization processing on the predicted multiple capacity difference values ​​and adding them to the capacity value of the previous cycle respectively to obtain multiple capacity values, and converting the multiple capacity values ​​into multiple SOH estimation values ​​according to the SOH formula.

7. A lithium battery health status prediction device based on hidden Markov model, characterized in that: include: The feature acquisition module is configured to acquire the voltage, charge and discharge time, maximum capacity of each cycle and temperature of the lithium battery, obtain the battery capacity increment curve, average temperature time curve and maximum capacity change curve according to the voltage, charge and discharge time, maximum capacity of each cycle and temperature, and use the extreme point, slope and mean of each curve as feature data; A correlation selection module is configured to calculate a correlation coefficient between the feature data and the actual value of SOH, and select an optimal feature combination based on the correlation coefficient; A model training module is configured to establish a capacity estimation model, wherein the capacity estimation model adopts a hidden Markov model and uses training data to train the capacity estimation model; The estimation module is configured to input 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, obtain the capacity estimation value according to the current capacity value and the capacity difference value, and obtain the SOH estimation value according to the capacity estimation value and the SOH definition. The estimation process of the capacity estimation model includes: The hidden Markov model is λ=(A, B, Π), (A, B, Π) is the input, λ is the output, where Π represents the initial probability distribution vector, A=(a ij ) N×N is the state transfer matrix, where a ij Describe the system from state S i Transfer to state S j The probability of, N represents the number of states contained in the model, B represents the probability density function of the observed value in each state; The hidden Markov model is initialized by using the Viterbi algorithm combined with the k-means algorithm to obtain an initial model; Using the Viterbi algorithm to find the optimal state sequence under the historical observation sequence and update the parameters of the initial model; Repeat the previous step until the model converges or exceeds the set maximum number of iterations, and the final model parameter λ i (i=1, 2, 3) output, the hidden estimated state of the hidden Markov model is divided into three states: rising state, falling state, and stable state, and the parameter set {λ1, λ2, λ3} of the hidden Markov model is obtained; Extract the state sequence o from the current monitoring data of the hidden Markov model, and determine the state classification to which it belongs according to the maximum similarity criterion: S i =argmaxP(o|λ i ),i∈{1,2,3}; Finally, the capacity estimate is obtained by adding the current capacity value to the capacity difference predicted for the next state: C t+1 =C t +HMM(S i ); The capacity estimate is converted to an SOH estimate using the SOH formula.

8. An electronic device comprising: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.