Lithium battery health state prediction method based on hidden Markov model, electronic equipment and medium

Abstract

The invention discloses a lithium battery health state prediction method based on a hidden Markov model, electronic equipment and a medium. The method comprises the following steps: determining factors influencing the health state of the lithium battery as charging and discharging parameters; establishing a relational expression among the health state of the lithium battery at the previous moment, the current charging and discharging parameters and the current health state; and establishing a knowledge base according to the relational expression, and further constructing a hidden Markov model to predict the health state of the lithium battery. According to the state attribute and the monitoring parameter of the corresponding lithium battery, the health state of the lithium battery is reliably predicted.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence, and more specifically, to a lithium battery health status prediction method based on a hidden Markov model, an electronic device and a medium. Background Art

[0002] Lithium batteries are important energy storage devices and are widely used in many fields. The health status of lithium batteries directly affects the continuous and stable output of electric energy. It is very necessary to predict their health status based on their relevant parameters. The existing lithium battery health status prediction technology is mainly based on a single parameter threshold detection method. This method does not consider the correlation between the various parameters of lithium batteries and the overall impact of each parameter on the battery health status, which leads to distorted prediction of lithium battery health status.

[0003] Therefore, it is necessary to develop a lithium battery health status prediction method, electronic device and medium based on hidden Markov model.

[0004] The information disclosed in the background technology section of the present invention is only intended to deepen the understanding of the general background technology of the present invention, and should not be regarded as acknowledging or suggesting in any form that the information constitutes the prior art already known to those skilled in the art. Summary of the invention

[0005] The present invention proposes a lithium battery health status prediction method, electronic equipment and medium based on a hidden Markov model, which can make a reliable prediction of the health status of a lithium battery according to the state attributes and monitoring parameters of the corresponding lithium battery.

[0006] In a first aspect, an embodiment of the present disclosure provides a method for predicting the health status of a lithium battery based on a hidden Markov model, comprising:

[0007] Determine the factors that affect the health status of lithium batteries as charging and discharging parameters;

[0008] Establish the relationship between the health status of the lithium battery at the previous moment, the current charge and discharge parameters and the current health status;

[0009] A knowledge base is established based on the relationship, and then a hidden Markov model is constructed to predict the health status of the lithium battery.

[0010] Preferably, the charging and discharging parameters include voltage, current and battery temperature.

[0011] Preferably, establishing the relationship between the health state of the lithium battery at a previous moment, the current charge and discharge parameters, and the current health state includes:

[0012] Assume that the lithium battery has n health states, and use S to represent the health state set of the lithium battery, and a k∈S represents the health state of the lithium battery at the kth moment, and its state transfer matrix is ​​A, so there are a0, a1, ..., a k-1 、a k 、a k+1 , …, a n Represents the health status sequence of lithium batteries calculated by time;

[0013] The charge and discharge parameters that affect the health status of lithium batteries constitute the monitoring vector p, which is composed of m related parameters. Then the correlation matrix between the health status of lithium batteries and the charge and discharge parameters is B, so there are p0, p1, ..., p k-1 、p k 、p k+1 ,…,p m Represents the monitoring vector sequence of lithium battery calculated by time;

[0014] Then determine the health status of the lithium battery at the previous moment and the impact of the current charging and discharging parameters on the current health status.

[0015] Preferably, the relationship is:

[0016] a k =F(a k-1 ,p k ,A,B)

[0017] Among them, a k-1 and a k They represent the health status of the lithium battery at the k-1th moment and the kth moment, respectively, and p k represents the lithium battery monitoring vector at the kth moment, A represents the health state transfer matrix of the lithium battery, and B represents the correlation matrix between the health state of the lithium battery and the charge and discharge parameters.

[0018] Preferably, it also includes:

[0019] The knowledge base is updated based on the predicted health status and charge and discharge parameters of the lithium battery.

[0020] In a second aspect, an embodiment of the present disclosure further provides an electronic device, the electronic device comprising:

[0021] A memory storing executable instructions;

[0022] A processor runs the executable instructions in the memory to implement the lithium battery health status prediction method based on the hidden Markov model.

[0023] In a third aspect, an embodiment of the present disclosure further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the method for predicting the health status of a lithium battery based on a hidden Markov model is implemented.

[0024] Its beneficial effects are:

[0025] The present invention utilizes the health status of the lithium battery at the previous moment and a set of current parameter data, and predicts the health status of the lithium battery based on the method of hidden Markov model. According to the health status of the lithium battery at the previous moment and the charge and discharge parameters, the health status of the lithium battery is predicted using the hidden Markov model; all relevant data of each state and parameter of the lithium battery of the predicted model or type are saved, and the knowledge of the lithium battery state transfer matrix and the monitoring parameter correlation matrix are saved to realize the analysis and prediction results of the lithium battery.

[0026] The methods and apparatus of the present invention have other features and advantages that will be apparent from, or will be described in detail in, the accompanying drawings and subsequent detailed descriptions incorporated herein, which together serve to explain the specific principles of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The above and other objects, features and advantages of the present invention will become more apparent through a more detailed description of exemplary embodiments of the present invention in conjunction with the accompanying drawings, wherein like reference numerals generally represent like components throughout the exemplary embodiments of the present invention.

[0028] Figure 1 A flowchart showing the steps of a method for predicting the health status of a lithium battery based on a hidden Markov model according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0029] The preferred embodiments of the present invention will be described in more detail below. Although the preferred embodiments of the present invention are described below, it should be understood that the present invention can be implemented in various forms and should not be limited to the embodiments set forth herein.

[0030] To facilitate understanding of the solutions and effects of the embodiments of the present invention, three specific application examples are given below. Those skilled in the art should understand that the examples are only for facilitating understanding of the present invention, and any specific details thereof are not intended to limit the present invention in any way.

[0031] Example 1

[0032] Figure 1 A flowchart showing the steps of a method for predicting the health status of a lithium battery based on a hidden Markov model according to an embodiment of the present invention is shown.

[0033] like Figure 1 As shown, the lithium battery health status prediction method based on the hidden Markov model includes:

[0034] Step 101, determining that the factors affecting the health status of the lithium battery are charge and discharge parameters;

[0035] Step 102, establishing a relationship between the health state of the lithium battery at the previous moment, the current charge and discharge parameters and the current health state;

[0036] Step 103, establishing a knowledge base according to the relationship, and then constructing a hidden Markov model to predict the health status of the lithium battery.

[0037] In one example, the charge and discharge parameters include voltage, current, and battery temperature.

[0038] In one example, establishing the relationship between the health state of the lithium battery at the previous moment, the current charge and discharge parameters, and the current health state includes:

[0039] Assume that the lithium battery has n health states, and use S to represent the health state set of the lithium battery, and a k ∈S represents the health state of the lithium battery at the kth moment, and its state transfer matrix is ​​A, so there are a0, a1, ..., a k-1 、a k 、a k+1 , …, a n Represents the health status sequence of lithium batteries calculated by time;

[0040] The charge and discharge parameters that affect the health status of lithium batteries constitute the monitoring vector p, which is composed of m related parameters. Then the correlation matrix between the health status of lithium batteries and the charge and discharge parameters is B, so there are p0, p1, ..., p k-1 、p k 、p k+1 ,…,p m Represents the monitoring vector sequence of lithium battery calculated by time;

[0041] Then determine the health status of the lithium battery at the previous moment and the impact of the current charging and discharging parameters on the current health status.

[0042] In one example, the relationship is:

[0043] a k =F(a k-1 ,p k ,A,B)

[0044] Among them, a k-1 and a k They represent the health status of the lithium battery at the k-1th moment and the kth moment, respectively, and p k represents the lithium battery monitoring vector at the kth moment, A represents the health state transfer matrix of the lithium battery, and B represents the correlation matrix between the health state of the lithium battery and the charge and discharge parameters.

[0045] In one example, it also includes:

[0046] The knowledge base is updated based on the predicted health status and charge and discharge parameters of the lithium battery.

[0047] Specifically, the relevant parameters that affect the health status of lithium batteries are analyzed. Since there are many factors that affect the health status of lithium batteries, in order to objectively and truly reflect the degree of their influence on the health status, it is necessary to analyze the correlation between each influencing factor and the health status of lithium batteries. Assume: There are n health states of lithium batteries, S represents the health state set of lithium batteries, and a i ∈S represents a certain health state of the lithium battery, q i Indicates that at a certain moment, the feature vector is composed of r factors. i With q i For correlation analysis, q i Reduce to a t-dimensional vector; then calculate the correlation between the t-dimensional eigenvector and itself, that is, the eigenvector q i and q i The correlation between q i Reduced to an m-dimensional vector.

[0048] Through theoretical analysis and experimental verification, the main factors affecting the health status of lithium batteries include charging and discharging parameters: voltage, current and battery temperature.

[0049] Determine the health status and operating parameters of the lithium battery, analyze the correlation between the health status and operating parameters, use the covariance matrix to analyze the correlation between influencing factors, and determine the charging and discharging parameters of the lithium battery.

[0050] The influence of the health state of the lithium battery at the previous moment and the current charge and discharge parameters on the health state is analyzed. Assume that the current health state of the lithium battery is only related to its health state at the previous moment and the current charge and discharge parameters. If the lithium battery has n health states, S is used to represent the health state set of the lithium battery, and a k ∈S represents the health state of the lithium battery at the kth moment, and its state transfer matrix is ​​A, so there are a0, a1, ..., a k-1 、a k 、a k+1 , ... represent the health status sequence of lithium batteries calculated by time; the charge and discharge parameters that affect the health status of lithium batteries constitute the monitoring vector p, which is generally composed of m related parameters. Then the correlation matrix (i.e., observation matrix) between the health status of lithium batteries and the charge and discharge parameters is B, so there are p0, p1, ..., p k-1 、p k 、p k+1 , ... represent the monitoring vector sequence of lithium battery calculated by time. Drawing on expert knowledge, the influence of the health state of lithium battery at the previous moment and the current charge and discharge parameters on the health state are determined as follows:

[0051] a k =F(a k-1 ,p k ,A,B)k∈N

[0052] where a k-1 and a k They represent the health status of the lithium battery at the k-1th moment and the kth moment, respectively, and p k represents the lithium battery monitoring vector at the kth moment, A represents the health state transfer matrix of the lithium battery, and B represents the correlation matrix (i.e., observation matrix) between the health state of the lithium battery and the charge and discharge parameters.

[0053] Based on the health status of the lithium battery at the previous moment and the current charge and discharge parameters, the hidden Markov model is constructed in combination with the knowledge base to predict the health status of the lithium battery and output the prediction results of the health status of the lithium battery. The prediction results are summarized and the corresponding battery health status and charge and discharge parameters and their prediction results are used as knowledge to update the knowledge base.

[0054] The present invention improves the accuracy of lithium battery health status prediction by analyzing the factors that affect the health status of lithium batteries and considering the correlation between the factors. The existing lithium battery health status related data and the experience of professional engineers are used to build a knowledge base, so that the technology has the ability to learn independently. According to the different types of lithium battery health status, the relevant charging and discharging parameters that affect the health status of lithium batteries are determined, and a health status prediction method for different types of lithium batteries is constructed based on the hidden Markov model, which ensures the applicability of this technology.

[0055] Through experimental testing, the present invention has a high accuracy in predicting the health status of lithium batteries, and with the accumulation of relevant data during use and the improvement of the expert knowledge base, the accuracy of the prediction results will gradually improve.

[0056] Example 2

[0057] The present disclosure provides an electronic device, which includes: a memory storing executable instructions; a processor, which runs the executable instructions in the memory to implement the above-mentioned lithium battery health status prediction method based on the hidden Markov model.

[0058] An electronic device according to an embodiment of the present disclosure includes a memory and a processor.

[0059] The memory is used to store non-temporary computer-readable instructions. Specifically, the memory may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may, for example, include random access memory (RAM) and / or cache memory (cache), etc. The non-volatile memory may, for example, include read-only memory (ROM), hard disk, flash memory, etc.

[0060] The processor may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device to perform desired functions. In one embodiment of the present disclosure, the processor is used to run the computer-readable instructions stored in the memory.

[0061] Those skilled in the art should be able to understand that in order to solve the technical problem of how to obtain a good user experience, the present embodiment may also include well-known structures such as a communication bus and an interface, and these well-known structures should also be included in the protection scope of the present disclosure.

[0062] For detailed description of this embodiment, reference may be made to the corresponding descriptions in the aforementioned embodiments, which will not be repeated here.

[0063] Example 3

[0064] An embodiment of the present disclosure provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the method for predicting the health status of a lithium battery based on a hidden Markov model is implemented.

[0065] According to the computer-readable storage medium of the embodiment of the present disclosure, non-transitory computer-readable instructions are stored thereon. When the non-transitory computer-readable instructions are executed by a processor, all or part of the steps of the above-mentioned methods of each embodiment of the present disclosure are executed.

[0066] The above-mentioned computer-readable storage media include, but are not limited to: optical storage media (e.g., CD-ROM and DVD), magneto-optical storage media (e.g., MO), magnetic storage media (e.g., magnetic tape or mobile hard disk), media with built-in rewritable non-volatile memory (e.g., memory card) and media with built-in ROM (e.g., ROM box).

[0067] Those skilled in the art should understand that the purpose of the above description of the embodiments of the present invention is only to exemplarily illustrate the beneficial effects of the embodiments of the present invention, and is not intended to limit the embodiments of the present invention to any given examples.

[0068] The embodiments of the present invention have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments.

Claims

1. A method for predicting the health status of a lithium battery based on a hidden Markov model, characterized in that: include: Determine the factors that affect the health status of lithium batteries as charging and discharging parameters; Establish the relationship between the health status of the lithium battery at the previous moment, the current charge and discharge parameters and the current health status; A knowledge base is established based on the relationship, and then a hidden Markov model is constructed to predict the health status of the lithium battery.

2. The lithium battery health status prediction method based on hidden Markov model according to claim 1, wherein: The charging and discharging parameters include voltage, current and battery temperature.

3. The method for predicting the health status of a lithium battery based on a hidden Markov model according to claim 1, wherein: Establishing the relationship between the health status of the lithium battery at the previous moment, the current charge and discharge parameters and the current health status includes: Assume that the lithium battery has n health states, and use S to represent the health state set of the lithium battery, and a k ∈S represents the health state of the lithium battery at the kth moment, and its state transfer matrix is ​​A, so there are a0, a1, ..., a k-1 、a k 、a k+1 , …, a n Represents the health status sequence of lithium batteries calculated by time; The charge and discharge parameters that affect the health status of lithium batteries constitute the monitoring vector p, which is composed of m related parameters. Then the correlation matrix between the health status of lithium batteries and the charge and discharge parameters is B, so there are p0, p1, ..., p k-1 、p k 、p k+1 ,…,p m Represents the monitoring vector sequence of lithium battery calculated by time; Then determine the health status of the lithium battery at the previous moment and the impact of the current charging and discharging parameters on the current health status.

4. The method for predicting the health status of a lithium battery based on a hidden Markov model according to claim 1, wherein: The relationship is: a k =F(a k-1 ,p k ,A,B) Among them, a k-1 and a k They represent the health status of the lithium battery at the k-1th moment and the kth moment, respectively, and p k represents the lithium battery monitoring vector at the kth moment, A represents the health state transfer matrix of the lithium battery, and B represents the correlation matrix between the health state of the lithium battery and the charge and discharge parameters.

5. The method for predicting the health status of a lithium battery based on a hidden Markov model according to claim 1, wherein: Also includes: The knowledge base is updated based on the predicted health status and charge and discharge parameters of the lithium battery.

6. An electronic device, characterized in that: The electronic device comprises: A memory storing executable instructions; A processor, wherein the processor runs the executable instructions in the memory to implement the following steps: Determine the factors that affect the health status of lithium batteries as charging and discharging parameters; Establish the relationship between the health status of the lithium battery at the previous moment, the current charge and discharge parameters and the current health status; A knowledge base is established based on the relationship, and then a hidden Markov model is constructed to predict the health status of the lithium battery.

7. The electronic device according to claim 6, wherein: The charging and discharging parameters include voltage, current and battery temperature.

8. The electronic device according to claim 6, wherein: Establishing the relationship between the health status of the lithium battery at the previous moment, the current charge and discharge parameters and the current health status includes: Assume that the lithium battery has n health states, and use S to represent the health state set of the lithium battery, and a k ∈S represents the health state of the lithium battery at the kth moment, and its state transfer matrix is ​​A, so there are a0, a1, ..., a k-1 、a k 、a k+1 , …, a n Represents the health status sequence of lithium batteries calculated by time; The charge and discharge parameters that affect the health status of lithium batteries constitute the monitoring vector p, which is composed of m related parameters. Then the correlation matrix between the health status of lithium batteries and the charge and discharge parameters is B, so there are p0, p1, ..., p k-1 、p k 、p k+1 ,…,p m Represents the monitoring vector sequence of lithium battery calculated by time; Then determine the health status of the lithium battery at the previous moment and the impact of the current charging and discharging parameters on the current health status.

9. The electronic device according to claim 6, wherein: The relationship is: a k =F(a k-1 ,p k ,A,B) Among them, a k-1 and a k They represent the health status of the lithium battery at the k-1th moment and the kth moment, respectively, and p k represents the lithium battery monitoring vector at the kth moment, A represents the health state transfer matrix of the lithium battery, and B represents the correlation matrix between the health state of the lithium battery and the charge and discharge parameters.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for predicting the health status of a lithium battery based on a hidden Markov model described in any one of claims 1 to 5 is implemented.

Images