Method, system and equipment for predicting service life of storage battery pack

Abstract

The invention discloses a method, a system and equipment for predicting the service life of a storage battery pack, and belongs to the technical field of storage batteries, the method, the system and the equipment for predicting the service life of the storage battery pack comprise the following steps: step 1, collecting working information of each battery to be managed in real time; step 2, obtaining transformation information of the predicted state transfer value of each battery according to the working information of each battery; 3, obtaining a battery life score of the battery according to the transformation information; in the technical scheme provided by the invention, the change information of the state transition value is utilized to predict the life score of the battery, so that the method has enough accuracy for a single battery in practice.

Description

Technical Field

[0001] The present application relates to the technical field of battery packs, and in particular to a method, system, and device for predicting the life of a battery pack. Background Art

[0002] In large photovoltaic power stations, energy storage power stations and other places, there are a large number of battery packs, which are distributed in various areas of the station to store the electricity generated by power generation. These battery packs are constantly charged and discharged during operation. At the same time, the batteries in the battery packs will gradually age and need to be repaired or replaced. In the prior art, the battery is maintained only after a battery failure occurs and a fault alarm is issued, which makes it impossible to manage the battery in a timely manner.

[0003] Currently, the expected life of a battery is predicted by directly fitting the battery's historical usage data with the battery's usage times, internal resistance and other data. For a single battery, this battery life prediction method has low accuracy. Summary of the invention

[0004] The content of this application is used to introduce concepts in a brief form, which will be described in detail in the detailed implementation section below. The content of this application is not intended to identify the key features or essential features of the technical solution claimed for protection, nor is it intended to limit the scope of the technical solution claimed for protection.

[0005] As a first aspect of the present application, in order to solve the technical problems mentioned in the above background technology section, the present application provides a method for predicting the life of a battery pack, comprising the following steps: Step 1: Collect the working information of each battery to be managed in real time; Step 2: Obtain transformation information of the estimated state transition value of each battery according to the working information of each battery; Step 3: Obtain the battery life score of the battery according to the transformed information; In the technical solution provided in the present application, the transformation information of the state transition value is used to predict the life score of the battery, so in practice, for a single battery, it has sufficient accuracy.

[0006] Furthermore, step 1 includes the following steps: The operating information includes the battery's internal resistance, discharge direction, and the amount of charge transferred.

[0007] In the existing technology, the evaluation of the expected state transition value of the battery is generally focused on the number of times the battery is used or the battery capacity of the battery, and it is difficult to describe the change information of the battery state. To address this problem, the present application provides the following technical solutions: Furthermore, step 2 includes the following steps: Step 21: Obtain the factory data of each battery, the factory data includes: the battery model and the production batch of the battery; Step 22: Collecting the working information of each battery in the battery pack; constructing a working distribution diagram of each battery using the working information; The vertical axis of the working distribution diagram is the internal resistance, the positive direction of the horizontal axis is the number of discharges, the positive direction of the horizontal axis is the number of charges, and each element in the working distribution diagram is the charge transfer amount; Step 23: Update the working distribution map of each battery in real time, and obtain the transformation information of the battery according to the working distribution map.

[0008] In the technical solution provided by the present application, by continuously updating the working distribution map of the battery, it is possible to perform adaptive state analysis on each battery, thereby increasing the accuracy of the prediction of the current life state of the battery.

[0009] Although the battery life is correlated with voltage, battery capacity, charging times and other information, in practice, it is not linearly correlated, that is, the battery life is not linearly related to the charging times or the internal resistance of the battery. Using a simple linear model to describe the aging state of the battery will result in low accuracy of the description. To address this problem, this application provides the following technical solutions: Further, step 23 includes the following steps: Step 231: construct a battery state transition model; Step 232: Construct a state distribution model based on the battery state transition model: Step 233: Obtain battery transformation information according to the state distribution model.

[0010] In the existing solutions, when building a battery state transition model, the following two solutions are generally used to build an aging model. The first solution is to directly set the change of battery life to an aging model that is linearly related to the degree of use. The second solution is to set the battery aging process to a multi-stage type to try to match the change of the internal resistance of the battery and the impact on the battery life model.

[0011] In practice, both of the above methods are difficult to fit the aging state of each battery. In fact, the aging life curves of batteries of the same model are actually inconsistent due to production batches or usage environment factors. In actual use, the fixed aging curve has limited accuracy in predicting the life state of a single battery. To address this problem, this application provides the following technical solutions: Step 231 includes the following steps: Step 2311: input the current working characteristic diagram of each battery into the matching database, the matching database is based on the pre-configured twin network model, and the closest aging curve is matched from the database; Step 2312: Based on the matched aging curve, obtain the number of aging states of the corresponding battery; Step 2313: Construct a battery state transition model based on the number of battery aging states.

[0012] In the technical solution provided by the present application, by comparing each battery with the information in the database, the closest aging curve can be matched, so that the aging trend of the battery can be roughly understood, and the success rate will be higher when the battery state transition model is constructed based on this.

[0013] Furthermore, the battery state transition model in step 231 is: T(t)=T1(t)+T2(t)+……T n (t)=a1F1(t)+a2F2(t)++......a n F n (t).

[0014] T1(t)=a1F1(t); T2(t)=a2F2(t); T n (t) = a n F n (t); The critical condition is: T n-1 (t) = T n (t); Where T(t) represents the state transition value T of the battery at time t, T1(t), T2(t), ...T n (t) are mathematical variables corresponding to the aging states of the order; a1, a2, ... a n is the fitting coefficient; F1(t), F2(t), ..., F n (t) is the preset initial function.

[0015] Furthermore, step 3 includes the following steps: Step 31: Setting the evaluation value of each transformation information; Step 32: The feature extraction model parses the current transformation information of the battery from the transformation information, and calculates the battery life score R according to the probability distribution of the current transformation information of the battery; R=pT i +(1-p)T i+1; Where R represents the battery life fraction, p represents the probability that the battery does not transition in the current state i, and (1-p) represents the probability that the battery transitions to the next state. T i+1 Indicates the estimated lifespan of the battery in the next tense. The calculation method of the estimated lifespan has been disclosed above.

[0016] As a second aspect of the present application, in order to solve the technical problems mentioned in the above background technology section, the present application provides a battery pack life prediction system, including: A terminal device, used for receiving the working information of each battery in each battery pack; and A first server executes the battery pack life prediction method; As a third aspect of the present application, in order to solve the technical problems mentioned in the above background technology section, the present application provides a terminal device, including: one or more processors; a memory for storing one or more computer programs, It is characterized in that the one or more processors execute the one or more computer programs to implement the steps of the battery pack life prediction method.

[0017] In summary, the technical solution provided in this application can accurately evaluate the expected service life of the battery. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings constituting a part of this application are used to provide a further understanding of this application, so that other features, purposes and advantages of this application become more obvious. The illustrative embodiment drawings and their descriptions of this application are used to explain this application and do not constitute an improper limitation on this application.

[0019] In addition, throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that the components and elements are not necessarily drawn to scale.

[0020] In the attached picture: Figure 1 A flowchart of a method for predicting the life of a battery pack; Figure 2 Schematic diagram of battery operating distribution diagram.

[0021] Figure 3 Schematic diagram of the battery aging curve. DETAILED DESCRIPTION

[0022] Embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms, and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present application. It should be understood that the drawings and embodiments of the present application are only for exemplary purposes and are not intended to limit the scope of protection of the present application.

[0023] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other.

[0024] The present application will be described in detail below with reference to the accompanying drawings and in combination with embodiments.

[0025] Example 1: Reference Figure 1 , a method for predicting the life of a battery pack comprises the following steps: Step 1: Collect the working information of each battery to be managed in real time.

[0026] The operating information includes the battery's internal resistance, discharge direction, and the amount of charge transferred.

[0027] The working information collected in this application includes the internal resistance of the battery, the discharge direction, and the amount of charge transfer. The internal resistance of the battery will change with the increase in the number of uses. In practice, a minimum resistance resolution needs to be set. The discharge direction refers to whether the battery is in a charging state or a discharging state.

[0028] In this way, for each use of the battery, the current internal resistance of the battery, the discharge direction, and the charge transfer amount can be obtained. The charge transfer amount is the amount of electricity released by the battery, or the amount of charge.

[0029] Step 2: Process the working information of each battery to obtain transformation information representing the expected state transition value of each battery.

[0030] Step 2 includes the following steps: Step 21: Obtain the factory data of each battery, the factory data includes: the battery model and the production batch of the battery.

[0031] The battery will continue to age as the working time increases, and the hallmark information of aging is actually the change in internal resistance. The factory voltage, factory battery capacity, and factory internal resistance of each type of battery are different, so directly using the battery's working information may not necessarily characterize the battery's health status. In addition, because the battery manufacturing process and manufacturer are different, the internal resistance of batteries of the same model is not necessarily the same. For this reason, it is necessary to obtain the battery's factory data and classify the batteries according to the factory data. The basis for classification is the battery model and production batch. Batteries with the same model and the same production batch are considered the same type of battery.

[0032] Step 22: Collecting the working information of each battery in the battery pack; constructing a working distribution diagram of each battery using the working information; The ordinate of the working distribution diagram is the internal resistance, the positive direction of the abscissa is the number of discharges, the negative direction of the abscissa is the number of charges, and each element in the working distribution diagram is the charge transfer amount.

[0033] like Figure 2 As shown, for each battery, a work distribution graph can be generated. The use of the battery can be distinguished in the work distribution graph. Each element in the work distribution graph shows a use record of the battery.

[0034] For example, the position of the element (1, 1) indicates that the internal resistance of the battery is 1 when it is discharged for the first time, and the discharge amount is the specific value of this position.

[0035] In practice, batteries can be matched according to the working distribution diagram. If two batteries with the same production model and the same production batch are similar in the working distribution diagram, the aging process of these two batteries will be very close.

[0036] Step 23: Update the working distribution map of each battery in real time, and obtain the transformation information of the battery according to the working distribution map.

[0037] In this solution, updating the working distribution map actually means matching the working distribution map of each battery currently required to be monitored with the working distribution map of each battery in the historical database to obtain the life status of each battery currently required to be monitored.

[0038] Step 23 includes the following steps: Step 231: Construct a battery state transition model.

[0039] The battery state transition model is actually used to analyze the probability of the battery transitioning to the next state under the current state. In order to accurately construct the battery state transition model, it is necessary to accurately obtain the number of states of the battery. To this end, this application provides the following solutions: Step 231 includes the following steps: Step 2311: Input the current operating characteristic diagram of each battery into the matching database. The matching database is based on a pre-configured twin network model and matches the closest aging curve from the database.

[0040] Specifically, a large number of battery operating characteristic diagrams and the battery aging curves are stored in the database. Therefore, if the closest operating characteristic diagram can be matched, the corresponding aging curve can be obtained.

[0041] In a more specific implementation, the following method is adopted: The twin network model is constructed as follows: two convolutional neural networks (CNNs) with the same structure and shared weights are constructed as input layers. The input layer accepts a pair of images as input.

[0042] Construct a similarity calculation layer: used to calculate the similarity or distance between two feature vectors. Commonly used similarity measurement methods include Euclidean distance, cosine similarity, etc.

[0043] In this application, cosine similarity is used to evaluate the similarity between two images.

[0044] In the data, at least three working characteristic diagrams are saved for each type of battery. Then, for the battery to be predicted, its working characteristic diagram is matched with the three working characteristic diagrams of the corresponding type of battery in turn, and the working characteristic diagram with the best matching result is selected.

[0045] The similarity between two images is calculated as follows: S1: Preprocess images 1 and 2. Preprocessing mainly involves unifying the calculation method of numerical values.

[0046] S2: Figure 1 and Figure 2 Input into the input layer, we get f(x1) and f(x2), f(x1) and f(x2) are Figure 1 and Figure 2 characteristics.

[0047] In this application, the main purpose is to extract the texture features in the input layer extraction work diagram, so as to facilitate the comparison of the similarity between the image 1 and the image 2 during use. The specific texture feature extraction method can use the SIFT algorithm.

[0048] S3: Input f(x1) and f(x2) into the similarity calculation layer to calculate the cosine similarity of the two images.

[0049] If the similarity between picture 1 and picture 2 is greater than a preset threshold, it means that the two match each other, and the corresponding curve can be obtained.

[0050] Step 2312: Based on the matched aging curve, obtain the number of aging states of the corresponding battery; Step 2313: Construct a battery state transition model based on the number of battery aging states.

[0051] The battery state transition model in step 231 is: T(t)=T1(t)+T2(t)+……T n (t)=a1F1(t)+a2F2(t)++......a n F n (t).

[0052] T1(t)=a1F1(t); T2(t)=a2F2(t); T n (t) = a n F n (t); The critical condition is: T n-1 (t) = T n (t); Where T(t) represents the state transition value T of the battery at time t, T1(t), T2(t), ...T n (t) are mathematical variables corresponding to the aging states of the order; a1, a2, ... a n is the fitting coefficient; F1(t), F2(t), ..., F n (t) is the preset initial function.

[0053] The aging of the battery is a slow process, but as the internal resistance of the battery increases, the heat generated by the battery during operation will become more and more serious, and the corresponding battery aging rate will gradually increase. Therefore, in the process of battery aging, it cannot be simply treated as a linear model. It is a process of gradual change. For this reason, in this application, according to the pre-matched aging curve, a battery state transition model is set for each battery according to its expected aging curve, so that the accuracy of the battery state transition model of each battery will be higher.

[0054] Among them, T(t) is actually the evaluation value of the expected life of the current battery. For specific evaluation methods, please refer to the battery life evaluation method in China Patent CN112731164B A battery life evaluation method. Or directly use the number of times the battery is used for evaluation. In other words, the value of T(t) is a fixed value that does not include a fixed value or reference value for the battery to transfer to the next state.

[0055] Step 232: construct a state distribution model based on the battery state transition model.

[0056] refer to Figure 3 In step 231, the battery aging model has been provided and fitted. The battery aging model is actually a mathematical representation of the battery aging curve. After obtaining the battery aging model, the battery aging curve is divided into several time states, and a state distribution model can be constructed. The specific construction method will not be further described here.

[0057] Step 233: Obtain battery transformation information according to the state distribution model.

[0058] In step 232, the battery aging model is divided into time states. The battery transformation information is the probability of the current state of the battery shifting to the next time state.

[0059] Step 3: Obtain the battery life score of the battery according to the battery transformation information; Step 3 includes the following steps: Step 31: Setting the evaluation value of each transformation information; Step 32: The feature extraction model parses the current transformation information of the battery from the transformation information, and calculates the battery life score R according to the probability distribution of the current transformation information of the battery; R=pT i +(1-p)T i+1 ; Where R represents the battery life fraction, p represents the probability that the battery does not transition in the current state i, and (1-p) represents the probability that the battery transitions to the next state. T i+1 Indicates the estimated lifespan of the battery in the next tense. The calculation method of the estimated lifespan has been disclosed above.

[0060] In the technical solution provided by the present application, the probability of the battery transferring to a subsequent state can be introduced when calculating the battery life score R, so that the battery usage can be accurately measured.

[0061] Embodiment 2: A battery life prediction system, comprising: A terminal device, used for receiving the working information of each battery in each battery pack; and A first server executes the battery pack life prediction method; Embodiment 3: A terminal device, comprising: one or more processors; a memory for storing one or more computer programs, It is characterized in that the one or more processors execute the one or more computer programs to implement the steps of the battery pack life prediction method.

[0062] The above description is only some preferred embodiments 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 embodiments of the present application is not limited to the technical solutions 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 (but not limited to) technical features with similar functions disclosed in the embodiments of the present application to form a technical solution.

Claims

1. A method for predicting the life of a battery pack, characterized in that: The steps include: Step 1: Collect the working information of each battery to be managed in real time; Step 2: Obtain transformation information of the estimated state transition value of each battery according to the working information of each battery; Step 3: Obtain the battery life score of the battery according to the transformed information.

2. The method for predicting the life of a battery pack according to claim 1, characterized in that: Step 1 includes the following steps: The operating information includes the battery's internal resistance, discharge direction, and the amount of charge transferred.

3. The method for predicting the life of a battery pack according to claim 1, characterized in that: Step 2 includes the following steps: Step 21: Obtain the factory data of each battery, the factory data includes: the battery model and the production batch of the battery; Step 22: Collecting the working information of each battery in the battery pack; constructing a working distribution diagram of each battery using the working information; The vertical axis of the working distribution diagram is the internal resistance, the positive direction of the horizontal axis is the number of discharges, the positive direction of the horizontal axis is the number of charges, and each element in the working distribution diagram is the charge transfer amount; Step 23: Update the working distribution map of each battery in real time, and obtain the transformation information of the battery according to the working distribution map.

4. The method for predicting the life of a battery pack according to claim 3, characterized in that: Step 23 includes the following steps: Step 231: construct a battery state transition model; Step 232: Construct a state distribution model based on the battery state transition model: Step 233: Obtain battery transformation information according to the state distribution model.

5. The method for predicting the life of a storage battery pack according to claim 4, characterized in that: Step 231 includes the following steps: Step 2311: input the current working characteristic diagram of each battery into the matching database, the matching database is based on the pre-configured twin network model, and the closest aging curve is matched from the database; Step 2312: Based on the matched aging curve, obtain the number of aging states of the corresponding battery; Step 2313: Construct a battery state transition model based on the number of battery aging states.

6. The method for predicting the life of a battery pack according to claim 5, characterized in that: The battery state transition model in step 231 is: T(t)=T1(t)+T2(t)+……T n (t)=a1F1(t)+a2F2(t)++……a n F n (t); T1(t)=a1F1(t); T2(t)=a2F2(t); T n (t)=a n F n (t); The critical condition is: T n-1 (t) = T n (t); Where T(t) represents the state transition value T of the battery at time t, T1(t), T2(t), ...T n (t) are mathematical variables corresponding to the aging states of the order; a1, a2, ... a n is the fitting coefficient; F1(t), F2(t), ..., F n (t) is the preset initial function.

7. The method for predicting the life of a battery pack according to claim 6, characterized in that: Step 3 includes the following steps: Step 31: Setting the evaluation value of each transformation information; Step 32: The feature extraction model parses the current transformation information of the battery from the transformation information, and calculates the battery life score R according to the probability distribution of the current transformation information of the battery; R=pT i +(1-p)T i+1 ; Where R represents the battery life fraction, p represents the probability that the battery does not transfer in the current state i, and (1-p) represents the probability that the battery transfers to the next state; T i+1 An estimated value indicating the expected life of the battery in the next tense.

8. A battery life prediction system, characterized in that: include: A terminal device, used for receiving the working information of each battery in each battery pack; as well as The first server executes the method according to any one of claims 1 to 7.

9. A terminal device, comprising: one or more processors; a memory for storing one or more computer programs, It is characterized in that the one or more processors execute the one or more computer programs to implement the steps of the method according to any one of claims 1 to 7.

Images