Battery diagnosis system and method

The battery diagnosis system uses a BMS and server to generate multiple diagnosis results, enabling accurate determination and control of battery states, ensuring safety by addressing the limitations of existing systems.

JP2025107172APending Publication Date: 2025-07-17LG ENERGY SOLUTION LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
JP2025033460
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Priority Date
2021-08-31
Filing Date
2025-03-04
Publication Date
2025-07-17

AI Technical Summary

Technical Problem

Existing battery diagnosis systems lack the capability to accurately determine the current state of a battery based on multiple diagnosis results and effectively control the battery accordingly.

Method used

A battery diagnosis system comprising a BMS that generates a first diagnosis result from battery information and a server that utilizes a pre-learned state estimation model to generate second and third diagnosis results, allowing for a comprehensive determination of the battery's current and future states, with the server determining the battery state based on these results and providing appropriate control measures.

Benefits of technology

The system enables accurate and reliable determination of the battery's state, reducing the risk of misdiagnosis and ensuring the battery remains in a safe condition by implementing appropriate control measures, including fire suppression if necessary.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2025107172000001_ABST
    Figure 2025107172000001_ABST
Patent Text Reader

Abstract

SOLUTION: A battery diagnosis system of one embodiment comprises: BMS for acquiring battery information which includes at least one of a temperature, a current, and a voltage of a battery, and generating a first diagnosis result corresponding to a current state of the battery on the basis of the battery information; and a server for receiving the battery information and the first diagnosis result from the BMS, generating a second diagnosis result corresponding to the current state of the battery and a third diagnosis result corresponding to a future state of the battery from the battery information, on the basis of a state estimation model learned in advance, then, determining the current state of the battery on the basis of multiple diagnosis results being the first, second, and third diagnosis results.SELECTED DRAWING: Figure 1
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This application claims priority based on Korean Patent Application No. 10-2021-0115865, filed on August 31, 2021, and all the contents disclosed in the specification and drawings of the said application are incorporated into this application in their entirety.

[0002] The present invention relates to a battery diagnosis system and method, and more particularly, to a battery diagnosis system and method for determining the current state of a battery based on diagnosis results in a battery management system (BMS) and a server.

Background Art

[0003] In recent years, the demand for portable electronic products such as notebook computers, video cameras, mobile phones, etc. has been rapidly increasing, and as the development of electric vehicles, energy storage batteries, robots, satellites, etc. has become full-scale, research on high-performance batteries that can be repeatedly charged and discharged has been actively conducted.

[0004] Currently, commercially available batteries include nickel-cadmium batteries, nickel-metal hydride batteries, nickel-zinc batteries, lithium batteries, etc. Among them, lithium batteries have attracted attention for their advantages of being able to be freely charged and discharged with almost no memory effect compared to nickel-based batteries, having a very low self-discharge rate, and having a high energy density.

[0005] Typical battery information for diagnosing the state of such a battery is temperature, voltage, and current, and based on such battery information, the state of the battery can be diagnosed. By diagnosing the state of the battery, it is possible to determine whether there is an abnormality in the battery or estimate the life of the battery, so it is preferable to periodically diagnose the state of the battery.

Summary of the Invention

Problems to be Solved by the Invention

[0006] The present invention has been made to solve the above problems, and an object thereof is to provide a battery diagnosis system and method capable of determining the current state of a battery based on a plurality of diagnosis results in a BMS and a server, and appropriately controlling the battery based on the determined current state.

[0007] Other objects and advantages of the present invention will be understood from the following description and will become more apparent from the embodiments of the present invention. Also, it will be easily understood that the objects and advantages of the present invention can be realized by the means and combinations thereof shown in the claims.

Means for Solving the Problems

[0008] A battery diagnosis system according to an aspect of the present invention includes a BMS that acquires battery information including at least one of the temperature, current, and voltage of the battery, and generates a first diagnosis result corresponding to the current state of the battery based on the battery information; and receives the battery information and the first diagnosis result from the BMS, and based on a pre-learned state estimation model, generates a second diagnosis result corresponding to the current state of the battery and a third diagnosis result corresponding to the future state of the battery from the battery information, and determines the current state of the battery based on a plurality of diagnosis results including the first diagnosis result, the second diagnosis result, and the third diagnosis result, and a server.

[0009] The diagnosis results may be configured to be classified into a first level, a second level, and a third level in order of the degree of danger to the battery.

[0010] The server may be configured to determine the current state according to a comparison result for the plurality of diagnosis results based on a preset battery state determination rule.

[0011] The server may be configured to determine whether the plurality of diagnostic results are the same, and determine the current state of the battery based on the determination result and the battery state determination rule.

[0012] When the plurality of diagnostic results are the same, the server may be configured to determine the current state of the battery so as to correspond to any one of the plurality of diagnostic results.

[0013] When the first diagnostic result is different from the second diagnostic result and the second diagnostic result is the same as the third diagnostic result, the server may be configured to receive the first diagnostic result from the BMS again over a predetermined time, and determine the current state of the battery based on the re-received first diagnostic result, the second diagnostic result, and the third diagnostic result.

[0014] The server may be configured to determine the level with the highest risk among the re-received first diagnostic result, the second diagnostic result, and the third diagnostic result as the current state of the battery.

[0015] When the first diagnostic result is the same as the second diagnostic result and the second diagnostic result is different from the third diagnostic result, the server may be configured to determine the level with the highest risk among the plurality of diagnostic results as the current state of the battery.

[0016] When the first diagnostic result is the same as the third diagnostic result and the third diagnostic result is different from the second diagnostic result, and when all of the plurality of diagnostic results are different, the server re-learns the state estimation model based on the battery information received from the BMS and cumulatively stored (saved), uses the re-learned state estimation model to re-generate the second diagnostic result and the third diagnostic result for the battery, and may be configured to diagnose the current state of the battery based on the first diagnostic result, the re-generated second diagnostic result, and the re-generated third diagnostic result.

[0017] If the first diagnostic result is the same as the regenerated second diagnostic result, and the regenerated third diagnostic result is different from the regenerated second diagnostic result, the server may be configured not to determine the current state of the battery and to output a notification for the occurrence of an abnormality in the state estimation model.

[0018] If all of the first diagnostic result, the regenerated second diagnostic result, and the regenerated third diagnostic result are different, the server may be configured to re-learn the state estimation model.

[0019] The server may be configured to determine a diagnostic measure for the battery corresponding to the determined current state of the battery and to transmit the determined diagnostic measure to the BMS.

[0020] The BMS may be configured to control the battery according to the diagnostic measure received from the server.

[0021] Based on the plurality of diagnostic results, the server may be configured to determine a fire occurrence level as the current state of the battery, and to determine, as a diagnostic measure corresponding to the determined fire occurrence level, any one of current limitation of the battery, a cooling operation for the battery, and fire suppression for the battery.

[0022] The battery diagnosis method according to another aspect of the present invention includes: a battery information acquisition step in which a BMS acquires battery information including at least one of a temperature, a current, and a voltage of a battery; a first diagnosis result generation step in which the BMS generates a first diagnosis result corresponding to a current state of the battery based on the battery information; a second and third diagnosis result generation step in which a server receives the battery information and the first diagnosis result from the BMS and generates, based on a pre-learned state estimation model, a second diagnosis result corresponding to the current state of the battery and a third diagnosis result corresponding to a future state of the battery from the battery information; and a current state determination step of the battery in which the server determines the current state of the battery based on a plurality of diagnosis results of the first diagnosis result, the second diagnosis result, and the third diagnosis result.

[0023] A server according to still another aspect of the present invention may include: a communication unit; and a processor that receives, via the communication unit, battery information including at least one of a temperature, a current, and a voltage of a battery and a first diagnosis result corresponding to a current state of the battery generated based on the battery information, generates, based on a pre-learned state estimation model, a second diagnosis result corresponding to the current state of the battery and a third diagnosis result corresponding to a future state of the battery from the battery information, and determines the current state of the battery based on the first diagnosis result, the second diagnosis result, and the third diagnosis result.

Advantages of the Invention

[0024] According to one aspect of the present invention, there is an advantage that the current state of the battery can be determined with high accuracy and reliability based on the diagnosis results for the battery generated by the BMS and the server.

[0025] The effects of the present invention are not limited to the above effects, and other effects not mentioned will be clearly understood by those skilled in the art from the description of the claims.

Brief Description of the Drawings

[0026] The following drawings attached to this specification serve to further understand the technical idea of the present invention together with the detailed description of the invention to be described later. Therefore, the present invention should not be construed as being limited only to the matters described in such drawings.

[0027]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Embodiments for Carrying Out the Invention

[0028] The terms and words used in this specification and the claims should not be construed as being limited to their ordinary or dictionary meanings. The inventor himself / herself must interpret them in accordance with the meaning and concept corresponding to the technical idea of the present invention in accordance with the principle that the concept of the terms can be appropriately defined in order to explain the invention in the best way.

[0029] Therefore, it should be understood that the embodiments described in this specification and the configurations shown in the drawings are only the most preferred embodiments of the present invention and do not represent all of the technical ideas of the present invention. Therefore, there may be various equivalents and modifications that can replace them at the time of this application.

[0030] In addition, in describing the present invention, if it is determined that a specific description of related known configurations or functions may obscure the gist of the present invention, the detailed description thereof will be omitted.

[0031] Terms including ordinal numbers such as first and second are used to distinguish any one of various components from other elements, and the components are not limited by these terms.

[0032] Throughout the specification, when a certain part "includes" a certain component, this means that, unless otherwise specified, it does not exclude other components, but may further include other components.

[0033] Furthermore, throughout the specification, when a certain part is "connected (coupled)" to another part, this includes not only the case where it is "directly connected (coupled)", but also the case where it is "indirectly connected (coupled)" with other elements interposed therebetween.

[0034] Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings.

[0035] FIG. 1 is a diagram schematically showing a battery diagnosis system according to an embodiment of the present invention. FIG. 2 is a diagram schematically showing an operation configuration of the battery diagnosis system according to an embodiment of the present invention.

[0036] Referring to FIG. 1, a battery diagnosis system 100 according to an embodiment of the present invention may include a BMS (Battery Management System) 110 and a server 120.

[0037] The BMS 110 means a battery management system capable of controlling a battery based on battery information (for example, temperature, voltage, and current). Since the BMS 110 is a configuration generally used in the battery-related field, a specific description of the BMS 110 itself will be omitted.

[0038] The BMS 110 may be configured to acquire battery information including at least one of the temperature, current, and voltage of the battery.

[0039] Here, the battery means one independent cell having a negative terminal and a positive terminal and being physically separable. For example, a lithium-ion battery or a lithium polymer battery can be regarded as a battery. Also, the battery can mean a battery module in which a plurality of cells are connected in series and / or in parallel. Hereinafter, for convenience of explanation, the battery will be described as meaning one independent cell.

[0040] And the BMS 110 may be configured to generate a first diagnostic result corresponding to the current state of the battery based on the battery information.

[0041] Specifically, the BMS 110 may generate a first diagnostic result for the battery according to a predetermined degree of risk based on the battery information. For example, the diagnostic results may be configured to be classified into a first level, a second level, and a third level in the order of the degree of risk for the battery. Here, the first level of the degree of risk may be set to be the lowest and the third level to be the highest.

[0042] Preferably, the BMS 110 may include a diagnostic algorithm capable of outputting a first diagnostic result corresponding to the current state of the battery from the battery information. Also, the BMS 110 may generate a first diagnostic result corresponding to the current state of the battery by inputting the battery information into the diagnostic algorithm.

[0043] The diagnostic algorithm may be provided to correspond to the storage (saving) capacity and performance of the BMS 110. For example, the diagnostic algorithm may include a learning model based on machine learning and / or a relational expression mapped to show the correspondence between the battery information and the current state of the battery.

[0044] Server 120 may be configured to receive battery information and a first diagnosis result from BMS 110.

[0045] Specifically, Server 120 and BMS 110 may be communicably connected. BMS 110 transmits the acquired battery information and the generated first diagnosis result to Server 120, and Server 120 can receive the battery information and the first diagnosis result. For this purpose, Server 120 may include a communication unit. For example, the communication unit can communicate with BMS 110 through a wireless communication method such as Wi-Fi (registered trademark), WFD (Wi-Fi Direct (registered trademark)), UWB (Ultra wideband), or mobile communication. Also, the communication unit can communicate with BMS 110 through a wired communication method such as a wired LAN (Local area network).

[0046] Server 120 may be configured to generate a second diagnosis result corresponding to the current state of the battery and a third diagnosis result corresponding to the future state of the battery from the battery information based on a pre-learned state estimation model.

[0047] Here, the state estimation model may be a learning model of a machine learning platform that estimates and outputs a diagnosis result corresponding to the current state and future state of the battery from the battery information. For example, the state estimation model provided in Server 120 may be an XGB (eXtreme Gradient Boosting) model. For this purpose, Server 120 may include a memory for storing the state estimation model.

[0048] Specifically, the server 120 can cumulatively store the battery information previously received from the BMS 110 and use the cumulatively stored battery information to train a state estimation model. Further, the server 120 can receive additional learning battery information from the outside or receive battery information from other BMSs, and train the state estimation model in consideration of all the received battery information. That is, the server 120 can use at least one of the battery information previously received from the BMS 110, the learning battery information received from the outside, and the battery information received from other BMSs to train the state estimation model so as to output a diagnosis result corresponding to the current state and future state of the battery from the input battery information.

[0049] In addition, the state estimation model can not only output a second diagnosis result corresponding to the current state of the battery, but also estimate and output a third diagnosis result corresponding to the future state of the battery. That is, the state estimation model may be configured to not only estimate the current state of the battery but also predict the future state of the battery. Here, similar to the first diagnosis result, the second diagnosis result and the third diagnosis result can be determined according to a predetermined level of risk based on the battery information. For example, the second diagnosis result and the third diagnosis result can be determined as the first level, the second level, or the third level according to the level of risk.

[0050] On the one hand, since the method of outputting different results (the first diagnostic result corresponding to the current state and the second diagnostic result corresponding to the future state) for the same input (battery information) can be derived by setting different types of parameters considered according to the learned content and different weighting values for the parameters, it should be noted that the specific content of one state estimation model being able to output different results (the second diagnostic result and the third diagnostic result) is omitted. Of course, according to the embodiment, the server 120 can also store, respectively, a first state estimation model that outputs a diagnostic result corresponding to the current state of the battery based on the input battery information, and a second state estimation model that outputs a diagnostic result corresponding to the future state of the battery based on the input battery information.

[0051] The server 120 may be configured to determine the current state of the battery based on a plurality of diagnostic results including the first diagnostic result, the second diagnostic result, and the third diagnostic result.

[0052] Specifically, the server 120 may determine the current state of the battery by considering all of the first diagnostic result generated by the BMS 110, the second diagnostic result directly generated, and the third diagnostic result.

[0053] Generally, the server 120 can process information with a larger capacity than the BMS 110. Therefore, the BMS 110 can quickly determine the state of the battery based on real-time battery information, and the server 120 can accurately determine the state of the battery based on the accumulated battery information. Also, in general, since the state of the battery determined by the server 120 is considered to be more accurate than the state of the battery determined by the BMS 110, it can be seen that the server 120 has a complementary and supplementary nature with respect to the BMS 110.

[0054] However, due to reasons such as data loss or errors during the learning process, it cannot be determined that the battery state determined by the server 120 is always more accurate than the battery state determined by the BMS 110. Therefore, the server 120 can determine the current state of the battery by considering not only the second and third diagnostic results directly generated but also the first diagnostic result generated by the BMS 110.

[0055] In addition, the server 120 can determine the current state of the battery by further considering not only the first and second diagnostic results corresponding to the current state of the battery but also the third diagnostic result corresponding to the future state of the battery predicted from the battery information. Therefore, by more conservatively determining the current state of the battery, the possibility of misdiagnosis regarding the state of the battery can be effectively reduced.

[0056] Therefore, the battery diagnostic system 100 according to an embodiment of the present invention has an advantage that it can determine the current state of the battery with high accuracy and reliability based on the diagnostic results for the battery generated by the BMS 110 and the server 120.

[0057] On the other hand, the server 120 may be configured to determine a diagnostic measure for the battery so as to correspond to the determined current state of the battery.

[0058] Here, the diagnostic measure may be a battery control measure preset to correspond to the current state of the battery, that is, the degree of risk to the battery. For example, the diagnostic measure may include at least one of a current cutoff measure, a cooling measure, and a fire suppression measure.

[0059] The server 120 may be configured to transmit the determined diagnostic measure to the BMS 110.

[0060] In addition, the BMS 110 may be configured to control the battery according to the diagnostic measure received from the server 120.

[0061] As a specific embodiment, an embodiment in which the battery diagnosis system 100 determines the fire level of the battery and performs a diagnosis on the determined fire level will be described.

[0062] The server 120 may determine the fire occurrence level based on a plurality of diagnosis results. That is, the server 120 may determine the fire occurrence level of the battery based on the first diagnosis result received from the BMS 110, the second diagnosis result directly generated, and the third diagnosis result.

[0063] For example, the fire occurrence level may include a first level corresponding to a normal state, a second level at which the temperature and / or pressure of the battery has increased to a first level, a third level at which the temperature and / or pressure of the battery has increased to a second level and there is a high possibility of fire occurrence, and a fourth level at which a fire has occurred in the battery.

[0064] The server 120 is configured to determine any one of battery state maintenance, battery current limitation, cooling operation for the battery, and fire suppression for the battery as a diagnostic measure corresponding to the determined fire occurrence level.

[0065] For example, when the determined fire occurrence level is the first level, since the battery is in a normal state, the server 120 may determine battery state maintenance as a diagnostic measure. In this case, there may be no separate control for the battery.

[0066] As another example, when the determined fire occurrence level is the second level, the server 120 may determine battery current limitation as a diagnostic measure. In this case, although the temperature and / or pressure of the battery has increased to the first level, the possibility of fire occurrence is low, so the amount of current flowing into the battery or discharged from the battery may be limited.

[0067] As yet another example, when the determined fire occurrence level is the third level, server 120 may determine a cooling operation for the battery as a diagnostic measure. In this case, since the temperature and / or pressure of the battery has become high at the second level and there is a high possibility of a fire occurring in the battery, a cooling measure may be taken for the battery to lower the temperature of the battery.

[0068] As yet another example, when the determined fire occurrence level is the fourth level, server 120 may determine fire suppression for the battery as a diagnostic measure. In this case, since a fire has occurred in the battery, measures for fire suppression may be taken. Here, fire suppression may be a measure of injecting carbon dioxide, fire extinguisher powder, etc. toward the battery.

[0069] Server 120 transmits diagnostic measures corresponding to the fire occurrence level for the battery to BMS 110, and BMS 110 can perform appropriate control measures corresponding to the current state of the battery by controlling the battery so as to correspond to the received diagnostic measures.

[0070] Therefore, the battery diagnostic system 100 according to an embodiment of the present invention can determine the current state of the battery based on a plurality of diagnostic results, and can always maintain the battery in a safe state by performing appropriate diagnostic measures corresponding to such a current state. Further, even when a fire occurs in the battery, the battery diagnostic system 100 can immediately perform fire suppression, so that a larger accident due to the fire can be prevented.

[0071] On the one hand, various operations of the server 120 described above may be executed by a processor of the server 120. Here, the processor may be, for example, a central processing unit (CPU), a microcontroller unit (MCU), a digital signal processor (DSP), or a field programmable gate array (FPGA).

[0072] Hereinafter, embodiments in which the server 120 determines the current state of the battery based on the first to third diagnostic results will be described in detail.

[0073] The server 120 may be configured to determine the current state according to the comparison result for a plurality of diagnostic results based on a preset battery state determination rule.

[0074] Specifically, the server 120 may be configured to determine whether a plurality of diagnostic results are the same, and determine the current state of the battery based on the determination result and the battery state determination rule.

[0075] FIG. 3 is a diagram for schematically explaining a determination rule corresponding to a diagnostic result according to various embodiments of the present invention. FIG. 4 is a diagram for schematically explaining various determination rules of the present invention.

[0076] First, among the embodiments of FIG. 3, the first embodiment will be described.

[0077] When a plurality of diagnostic results are the same, the server 120 may be configured to determine the current state of the battery so as to correspond to any one of the plurality of diagnostic results.

[0078] For example, referring to the first embodiment among the embodiments of FIG. 3, all of the first to third diagnostic results may be the same as A. In this case, the server 120 may determine the current state of the battery according to the first decision rule. Then, the server 120 may determine A as the current state of the battery. That is, referring to FIG. 4, since the first decision rule determines any one of the first diagnostic result, the second diagnostic result, and the third diagnostic result as the current state of the battery, when all of the plurality of diagnostic results are the same, the server 120 can determine the current state of the battery to correspond to any one of the diagnostic results.

[0079] Next, the second embodiment among the embodiments of FIG. 3 will be described.

[0080] When the first diagnostic result is different from the second diagnostic result and the second diagnostic result is the same as the third diagnostic result, the server 120 may be configured to re - receive the first diagnostic result from the BMS110 over a predetermined time and determine the current state of the battery based on the re - received first diagnostic result, the second diagnostic result, and the third diagnostic result.

[0081] After that, the server 120 may be configured to determine the level with the highest risk among the re - received first diagnostic result, the second diagnostic result, and the third diagnostic result as the current state of the battery.

[0082] For example, referring to the second embodiment among the embodiments of FIG. 3, the first diagnostic result may be A, and the second diagnostic result and the third diagnostic result may be B. In this case, the server 120 may determine the current state of the battery according to the second decision rule. The server 120 may re - receive the first diagnostic result from the BMS110 and re - determine the current state of the battery based on the re - received first diagnostic result, the pre - generated second diagnostic result, and the third diagnostic result.

[0083] Next, the third embodiment among the embodiments of FIG. 3 will be described.

[0084] Server 120 may be configured to determine, as the current state of the battery, the level with the highest risk among a plurality of diagnostic results when the first diagnostic result and the second diagnostic result are the same and the second diagnostic result and the third diagnostic result are different.

[0085] For example, referring to the third embodiment among the embodiments of FIG. 3, the first diagnostic result and the second diagnostic result may be A, and the third diagnostic result may be B. In this case, server 120 may determine the current state of the battery according to the third decision rule. Server 120 may also determine, as the current state of the battery, the diagnostic result with a higher risk between A and B.

[0086] Next, the fourth embodiment among the embodiments of FIG. 3 will be described.

[0087] When the first diagnostic result and the third diagnostic result are the same and the third diagnostic result and the second diagnostic result are different, server 120 may re-learn the state estimation model based on the accumulated battery information, use the re-learned state estimation model to re-generate the second diagnostic result and the third diagnostic result for the battery, and be configured to diagnose the current state of the battery based on the first diagnostic result, the re-generated second diagnostic result, and the re-generated third diagnostic result.

[0088] For example, referring to the fourth embodiment among the embodiments of FIG. 3, the first diagnostic result and the third diagnostic result may be A, and the second diagnostic result may be B. In this case, server 120 may determine the current state of the battery according to the fourth to sixth decision rules. Server 120 may re-learn the state estimation model and use the re-learned state estimation model to re-generate the second diagnostic result and the third diagnostic result. Then, server 120 can re-diagnose the current state of the battery according to the first diagnostic result received from BMS110, the re-generated second diagnostic result, and the re-generated third diagnostic result.

[0089] Finally, the fifth embodiment among the embodiments of FIG. 3 will be described.

[0090] When all of the plurality of diagnostic results are different, the server 120 may re-learn the state estimation model based on the accumulated battery information, re-generate the second diagnostic result and the third diagnostic result for the battery using the re-learned state estimation model, and diagnose the current state of the battery based on the first diagnostic result, the re-generated second diagnostic result, and the re-generated third diagnostic result.

[0091] For example, referring to the fifth embodiment among the embodiments of FIG. 3, the first diagnostic result may be A, the second diagnostic result may be B, and the third diagnostic result may be C. In this case, the server 120 may determine the current state of the battery according to the fourth to sixth decision rules. The server 120 may re-learn the state estimation model and re-generate the second diagnostic result and the third diagnostic result using the re-learned state estimation model. Then, the server 120 can re-diagnose the current state of the battery according to the first diagnostic result, the re-generated second diagnostic result, and the re-generated third diagnostic result received from the BMS 110.

[0092] That is, in the fourth and fifth embodiments among the embodiments of FIG. 3, the server 120 can determine the current state of the battery according to the fourth to sixth decision rules.

[0093] First, the server 120 re-learns the state estimation model based on the accumulated battery information according to the fourth decision rule, and re-generates the second diagnostic result and the third diagnostic result based on the re-learned state estimation model. Then, the server 120 can apply the first to third decision rules to the first diagnostic result, the re-generated second diagnostic result, and the re-generated third diagnostic result to determine the current state of the battery. For example, if the first diagnostic result, the re-generated second diagnostic result, and the re-generated third diagnostic result correspond to the first to third embodiments of FIG. 3, the server 120 can determine the current state of the battery according to the first to third decision rules.

[0094] If the first diagnostic result, the regenerated second diagnostic result, and the regenerated third diagnostic result correspond to the fourth embodiment of FIG. 3, the server 120 may not determine the current state of the battery according to the fifth decision rule and may output a notification. That is, if the first diagnostic result and the regenerated third diagnostic result are the same and the regenerated second diagnostic result and the regenerated third diagnostic result are different, the server 120 may not determine the current state of the battery according to the fifth decision rule and may be configured to output a notification for an abnormality occurrence in the state estimation model.

[0095] If the first diagnostic result, the regenerated second diagnostic result, and the regenerated third diagnostic result correspond to the fifth embodiment of FIG. 3, the server 120 may determine the current state of the battery according to the sixth decision rule. That is, if the first diagnostic result, the regenerated second diagnostic result, and the regenerated third diagnostic result are all different, the server 120 may re-learn the state estimation model according to the sixth decision rule. Also, the server 120 may regenerate the second diagnostic result and the third diagnostic result based on the re-learned state estimation model. The server 120 may determine the current state of the battery based on the first diagnostic result, the regenerated second diagnostic result, and the regenerated third diagnostic result. Here, the server 120 may determine the embodiment corresponding to the first diagnostic result, the regenerated second diagnostic result, and the regenerated third diagnostic result among the first to fifth embodiments of FIG. 3, and may determine the current state of the battery according to the determined embodiment.

[0096] The BMS 110 according to the present invention may be provided in a battery pack. That is, the battery pack according to the present invention may include the above-described BMS 110 and one or more battery cells. Further, the battery pack may further include electrical components (such as relays and fuses) and a case.

[0097] FIG. 5 is a diagram showing an exemplary configuration of a battery pack including the BMS 110 according to an embodiment of the present invention.

[0098] The positive terminal of the battery B may be connected to the positive terminal P+ of the battery pack 10, and the negative terminal of the battery B may be connected to the negative terminal P- of the battery pack 10.

[0099] The measurement unit 111 may be connected to the first sensing line SL1, the second sensing line SL2, the third sensing line SL3, and the fourth sensing line SL4.

[0100] Specifically, the measurement unit 111 may be connected to the positive terminal of the battery B via the first sensing line SL1 and to the negative terminal of the battery B via the second sensing line SL2. The measurement unit 111 can measure the voltage of the battery B based on the voltages measured on each of the first sensing line SL1 and the second sensing line SL2.

[0101] Also, the measurement unit 111 may be connected to the current measurement unit A via the third sensing line SL3. For example, the current measurement unit A may be an ammeter or a shunt resistor that can measure the charging current and the discharging current of the battery B. The measurement unit 111 can measure the charging current of the battery B via the third sensing line SL3 and calculate the charge amount. Also, the measurement unit 111 can measure the discharging current of the battery B via the third sensing line SL3 and calculate the discharge amount.

[0102] Also, the measurement unit 111 can measure the temperature of the battery B via the fourth sensing line SL4.

[0103] The voltage, current, and temperature of the battery B measured by the measurement unit 111 may be transmitted to the control unit 112 and the storage unit 113.

[0104] The control unit 112 can generate a first diagnostic result corresponding to the current state of the battery B based on the battery information received from the measurement unit 111. Then, the control unit 112 can transmit the generated first diagnostic result to the server 120. Further, the control unit 112 can receive a diagnostic measure corresponding to the battery B from the server 120, and limit the current amount of the battery B or perform cooling or fire suppression on the battery B in accordance with the received diagnostic measure.

[0105] On the other hand, the control unit provided in the BMS 110 may selectively include a processor, an application-specific integrated circuit (ASIC), other chip sets, logic circuits, registers, communication modems, data processing devices, etc., known in the art, in order to execute various control logics performed in the present invention. Further, when the control logic is implemented by software, the control unit may be implemented by a set of program modules. At this time, the program modules are stored in the memory and can be executed by the control unit. The memory may be inside or outside the control unit and may be connected to the control unit by various well-known means.

[0106] Further, the BMS 110 may further include a storage unit. The storage unit can store data, programs, or data generated during the operation and function of each component of the BMS 110, etc. The storage unit is not particularly limited as long as it is a known information storage means capable of recording, erasing, updating, and reading data. As an example, the information storage means may include RAM, flash memory (registered trademark), ROM, EEPROM, registers, etc. Further, the storage unit may store program codes defining processes executable by the control unit.

[0107] FIG. 6 is a diagram schematically showing a battery diagnosis method according to another embodiment of the present invention.

[0108] Preferably, each step of the battery diagnosis method can be performed by the battery diagnosis system 100. Hereinafter, for convenience of explanation, the content overlapping with the above-described content will be omitted or briefly described.

[0109] Referring to FIG. 6, the battery diagnosis method may include a battery information acquisition step, a first diagnosis result generation step, second and third diagnosis result generation steps, and a current state determination step of the battery.

[0110] The battery information acquisition step is a step of acquiring battery information including at least one of the temperature, current, and voltage of the battery, and can be performed by the BMS 110.

[0111] The first diagnosis result generation step is a step of generating a first diagnosis result corresponding to the current state of the battery based on the battery information, and can be performed by the BMS110.

[0112] For example, the BMS110 can generate a first diagnosis result corresponding to the current state of the battery by inputting the battery information into a provided diagnosis algorithm.

[0113] The second and third diagnosis result generation steps are steps of receiving the battery information and the first diagnosis result from the BMS110, and based on a pre-learned state estimation model, generating a second diagnosis result corresponding to the current state of the battery and a third diagnosis result corresponding to the future state of the battery from the battery information, and can be performed by the server 120.

[0114] For example, the server 120 can generate a second diagnosis result corresponding to the current state of the battery and a third diagnosis result corresponding to the future state of the battery by inputting the battery information into a pre-learned state estimation model.

[0115] The battery current state determination step is a step of determining the current state of the battery based on a plurality of diagnostic results including a first diagnostic result, a second diagnostic result, and a third diagnostic result, and can be performed by the server 120.

[0116] For example, referring to FIGS. 3 and 4, the server 120 determines the current state of the battery based on determination rules corresponding to the first diagnostic result, the second diagnostic result, and the third diagnostic result.

[0117] Also, referring to FIG. 6, the battery diagnostic method may further include a diagnostic measure determination step (S500) and a battery control step (S600).

[0118] The diagnostic measure determination step (S500) is a step of determining a diagnostic measure for the battery so as to correspond to the determined current state of the battery, and can be performed by the server 120.

[0119] For example, a plurality of diagnostic measures can be set according to the degree of danger to the battery, and the server 120 can determine a diagnostic measure corresponding to the current state of the battery. The diagnostic measures may include at least one of a current cutoff measure, a cooling measure, and a fire suppression measure.

[0120] The battery control step (S600) is a step of controlling the battery by the diagnostic measure determined in the diagnostic measure determination step (S500), and can be performed by the BMS 110.

[0121] First, the BMS 110 can receive the determined diagnostic measure from the server 120. Then, the BMS 110 can control the battery by the diagnostic measure determined by the server 120.

[0122] For example, the BMS 110 can maintain the state of the battery or cut off the current of the battery according to the current state of the battery. Further, the BMS 110 can execute cooling measures or fire suppression according to the current state of the battery.

[0123] According to an embodiment of the present invention, by determining the current state of the battery based on a plurality of diagnostic results and performing appropriate diagnostic measures corresponding to such a current state, the battery can always be maintained in a safe state. Further, even when a fire occurs in the battery, immediate fire suppression is performed, so that a larger accident caused by the fire can be prevented.

[0124] The embodiments of the present invention described above are not only realized by a system and a method, but may also be realized via a program that realizes functions corresponding to the configuration of the embodiments of the present invention or a recording medium on which such a program is recorded. Such realization can be easily achieved by those skilled in the technical field to which the present invention pertains from the description of the above-described embodiments.

[0125] As described above, the present invention has been described with reference to limited embodiments and drawings, but the present invention is not limited thereto, and it goes without saying that various modifications and variations can be made by those having ordinary knowledge in the technical field to which the present invention pertains within the equivalent scope of the technical idea and claims of the present invention.

[0126] Further, the present invention described above can be variously substituted, modified, and changed by those having ordinary knowledge in the technical field to which the present invention pertains without departing from the technical idea of the present invention. Therefore, it is not limited by the above-described embodiments and the accompanying drawings, and all or part of each embodiment can be selectively combined and configured for various modifications.

Description of Reference Numerals

[0127] 10 Battery Pack 100 Battery Diagnostic System 110 BMS 111 Measurement unit 112 Control unit 113 Memory unit 120 Server

Claims

1. A BMS that acquires battery information including at least one of the temperature, current, and voltage of a battery, and generates a first diagnostic result corresponding to the current state of the battery based on the battery information; A server that receives the battery information and the first diagnostic result from the BMS, generates a second diagnostic result corresponding to the current state of the battery and a third diagnostic result corresponding to the future state of the battery from the battery information based on a pre-learned state estimation model, and when the first diagnostic result, the second diagnostic result, and the third diagnostic result are the same, determines the current state of the battery so as to correspond to any one of the first diagnostic result, the second diagnostic result, and the third diagnostic result; A battery diagnostic system including the above.

2. A BMS that acquires battery information including at least one of the temperature, current, and voltage of a battery, and generates a first diagnostic result corresponding to the current state of the battery based on the battery information; A server that receives the battery information and the first diagnostic result from the BMS, and generates a second diagnostic result corresponding to the current state of the battery and a third diagnostic result corresponding to the future state of the battery from the battery information based on a pre-learned state estimation model; Including The first diagnostic result, the second diagnostic result, and the third diagnostic result are classified into a first level, a second level, and a third level in the order of the degree of danger to the battery, When the first diagnostic result and the second diagnostic result are different and the second diagnostic result and the third diagnostic result are the same, the server re-receives the first diagnostic result from the BMS over a predetermined time, and among the re-received first diagnostic result, the second diagnostic result, and the third diagnostic result, determines the current state of the battery as the level with the highest degree of danger. A battery diagnostic system.

3. A BMS that acquires battery information including at least one of the temperature, current, and voltage of a battery, and generates a first diagnostic result corresponding to the current state of the battery based on the battery information; A server that receives the battery information and the first diagnostic result from the BMS, and generates a second diagnostic result corresponding to the current state of the battery and a third diagnostic result corresponding to the future state of the battery from the battery information based on a pre-trained state estimation model. including The first diagnostic result, the second diagnostic result, and the third diagnostic result are classified into a first level, a second level, and a third level in the order of the degree of danger to the battery. The server determines the level with the highest degree of danger among the first diagnostic result, the second diagnostic result, and the third diagnostic result as the current state of the battery when the first diagnostic result and the second diagnostic result are the same and the second diagnostic result and the third diagnostic result are different. A battery diagnostic system.

4. A BMS that acquires battery information including at least one of the temperature, current, and voltage of the battery, and generates a first diagnostic result corresponding to the current state of the battery based on the battery information. A server that receives the battery information and the first diagnostic result from the BMS, generates a second diagnostic result corresponding to the current state of the battery and a third diagnostic result corresponding to the future state of the battery from the battery information based on a pre-trained state estimation model. When the first diagnostic result and the third diagnostic result are the same and the third diagnostic result and the second diagnostic result are different, or when the first diagnostic result, the second diagnostic result, and the third diagnostic result are all different, the state estimation model is re-learned based on the battery information received from the BMS and accumulated and stored, and the re-learned state estimation model is used to re-generate the second diagnostic result and the third diagnostic result for the battery, and diagnose the current state of the battery based on the first diagnostic result, the re-generated second diagnostic result, and the re-generated third diagnostic result. including The first diagnostic result, the second diagnostic result, and the third diagnostic result are classified into a first level, a second level, and a third level in the order of the degree of danger to the battery. A battery diagnostic system.

5. The server When the first diagnostic result and the regenerated third diagnostic result are the same and the regenerated third diagnostic result and the regenerated second diagnostic result are different, the battery diagnosis system according to claim 4 does not determine the current state of the battery and outputs a notification of an abnormality occurrence in the state estimation model.

6. The server When the first diagnostic result, the regenerated second diagnostic result, and the regenerated third diagnostic result are all different, the battery diagnosis system according to claim 4 retrains the state estimation model.

7. The server Determines a diagnostic measure for the battery so as to correspond to the determined current state of the battery, and transmits the determined diagnostic measure to the BMS. The BMS Controls the battery by the diagnostic measure received from the server, the battery diagnosis system according to any one of claims 1 to 6.

8. The server Based on the first diagnostic result, the second diagnostic result, and the third diagnostic result, determines a fire occurrence level corresponding to the current state of the battery, and as a diagnostic measure corresponding to the determined fire occurrence level, determines any one of current limitation of the battery, a cooling operation for the battery, and fire suppression for the battery, the battery diagnosis system according to claim 7.