Apparatus and method for diagnosing battery

Abstract

An apparatus for diagnosing a battery, according to one embodiment of the present invention, comprises: a profile acquisition unit configured to acquire one or more profiles by using voltage and capacity of a battery; an image conversion unit configured to convert each of the one or more profiles into an image and to generate a diagnostic image from the one or more converted images; and a control unit configured to diagnose a state of the battery corresponding to the diagnostic image by using a previously trained diagnostic model.

Description

Battery diagnostic device and method

[0001] This application claims priority to Korean Patent Application No. 10-2024-0014383, filed on January 30, 2024, the entire contents of which are disclosed in the specification and drawings of the said application are incorporated herein by reference.

[0002] The present invention relates to a battery diagnostic device and method, and more particularly, to a battery diagnostic device and method for diagnosing the state of a battery.

[0003] Recently, as the demand for portable electronic products such as laptops, video cameras, and mobile phones has rapidly increased, and the development of electric vehicles, energy storage batteries, robots, and satellites has been in full swing, research into high-performance batteries capable of repeated charging and discharging is actively being conducted.

[0004] Currently commercialized batteries include nickel-cadmium batteries, nickel-hydrogen batteries, nickel-zinc batteries, and lithium batteries. Among these, lithium batteries are receiving attention for their advantages of being able to charge and discharge freely, having a very low self-discharge rate, and having a high energy density, as they have almost no memory effect compared to nickel-based batteries.

[0005] While extensive research is being conducted on these batteries to improve capacity and density, improving lifespan and safety is also crucial. To improve battery safety, technology is required to accurately diagnose battery condition.

[0006] In particular, if a problem occurs with an operating battery, it can result in loss of life and financial losses. Therefore, technology is needed to predict battery condition in advance and prevent unexpected accidents.

[0007] The present invention has been devised to solve the above problems, and its purpose is to provide a battery diagnostic device and method for diagnosing the state of a battery.

[0008] Other objects and advantages of the present invention can be understood through the following description and will be more clearly understood through the embodiments of the present invention. Furthermore, it will be readily apparent that the objects and advantages of the present invention can be realized by the means and combinations thereof set forth in the claims.

[0009] A battery diagnostic device according to one aspect of the present invention may include a profile acquisition unit configured to acquire one or more profiles based on voltage and capacity of a battery; an image conversion unit configured to convert each of the one or more profiles into an image and generate a diagnostic image from the converted one or more images; and a control unit configured to diagnose a state of the battery corresponding to the diagnostic image using a pre-learned diagnostic model.

[0010] The above diagnostic model can be trained to determine the state of the battery from the diagnostic image through preset learning data.

[0011] The control unit may be configured to diagnose the state of the battery corresponding to the target cycle from the diagnostic image using the diagnostic model.

[0012] The image conversion unit may be configured to convert a profile for a cycle less than or equal to a preset reference cycle corresponding to the target cycle among the one or more profiles into an image.

[0013] The above reference cycle may be preset as a cycle in which the accuracy of the verification result for the target cycle is greater than or equal to a preset reference value during the verification process of the diagnostic model for preset verification data.

[0014] The above reference cycle may be preset as the lowest cycle among a plurality of cycles in which the accuracy of the verification result is greater than or equal to the reference value.

[0015] The above diagnostic model may be configured to generate a diagnostic result image that displays key areas considered in determining the condition of the battery in the entire area of ​​the diagnostic image.

[0016] The above diagnostic model can be configured to further indicate the importance of the key area in the diagnostic result image.

[0017] The above diagnostic model can be configured to display an area in the entire area of ​​the diagnostic image where the importance is greater than a preset threshold as the main area.

[0018] The control unit may be configured to diagnose the cause of the condition of the battery as one of a plurality of preset reference causes and set the usage conditions of the battery to correspond to the diagnosis result.

[0019] The image conversion unit may be configured to generate the diagnostic image by synthesizing one or more images.

[0020] A battery pack according to another aspect of the present invention may include a battery diagnostic device according to one aspect of the present invention.

[0021] A server according to another aspect of the present invention may include a battery diagnostic device according to one aspect of the present invention.

[0022] A battery diagnosis method according to another aspect of the present invention may include a profile acquisition step of acquiring one or more profiles based on the voltage and capacity of the battery; an image conversion step of converting each of the one or more profiles into an image and generating a diagnostic image from the converted one or more images; and a diagnosis step of diagnosing the state of the battery corresponding to the diagnostic image using a pre-learned diagnostic model.

[0023] According to one aspect of the present invention, since the battery diagnosis device diagnoses the state of the battery through an image, it has the advantage of being able to quickly diagnose the state of the battery using an image of the battery profile.

[0024] Furthermore, according to one aspect of the present invention, the battery diagnostic device can not only track and diagnose the battery's condition from the past to the present, but can also predict its future condition. Because it can track the battery's condition throughout its entire life cycle, the battery diagnostic device can proactively identify potential battery problems.

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

[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 described below, and therefore the present invention should not be interpreted as being limited to the matters described in such drawings.

[0027] FIG. 1 is a schematic diagram illustrating a battery diagnostic device according to one embodiment of the present invention.

[0028] FIG. 2 is a schematic diagram illustrating a plurality of profiles according to one embodiment of the present invention.

[0029] FIG. 3 is a diagram schematically illustrating the verification result of a diagnostic model according to one embodiment of the present invention.

[0030] Figures 4 to 7 are schematic diagrams illustrating diagnostic result images according to one embodiment of the present invention.

[0031] FIG. 8 is a schematic drawing of a battery pack according to another embodiment of the present invention.

[0032] FIG. 9 is a schematic diagram illustrating a server according to another embodiment of the present invention.

[0033] FIG. 10 is a diagram schematically illustrating a battery diagnosis method according to another embodiment of the present invention.

[0034] Terms or words used in this specification and claims should not be interpreted as limited to their usual or dictionary meanings, but should be interpreted as meanings and concepts that conform to the technical spirit of the present invention, based on the principle that the inventor can appropriately define the concept of the term to explain his or her own invention in the best possible manner.

[0035] Accordingly, the embodiments described in this specification and the configurations illustrated in the drawings are merely the most preferred embodiments of the present invention and do not represent all of the technical ideas of the present invention. Therefore, it should be understood that there may be various equivalents and modified examples that can replace them at the time of filing this application.

[0036] In addition, when describing the present invention, if it is determined that a detailed description of a related known configuration or function may obscure the gist of the present invention, the detailed description is omitted.

[0037] Terms that include ordinal numbers, such as first, second, etc., are used to distinguish one of the various components from the rest, and are not used to limit the components by such terms.

[0038] Throughout the specification, whenever a part is said to "include" a component, this does not mean that it excludes other components, but rather that it may include other components, unless otherwise stated.

[0039] Additionally, throughout the specification, when we say that a part is "connected" to another part, this includes not only cases where it is "directly connected" but also cases where it is "indirectly connected" with other elements in between.

[0040]

[0041] Hereinafter, a preferred embodiment of the present invention will be described in detail with reference to the attached drawings.

[0042] FIG. 1 is a schematic diagram illustrating a battery diagnostic device (100) according to one embodiment of the present invention.

[0043] Referring to FIG. 1, the battery diagnostic device (100) may include a profile acquisition unit (110), an image conversion unit (120), and a control unit (130).

[0044] Here, a battery refers to a physically separate, independent cell having a negative terminal and a positive terminal. For example, a lithium-ion battery or a lithium polymer battery may be considered a battery. Furthermore, the battery may be of a cylindrical type, a prismatic type, or a pouch type. Furthermore, a battery may also refer to a battery bank, a battery module, or a battery pack in which multiple cells are connected in series and / or parallel. For convenience of explanation, the term "battery" will be described herein below as referring to a single, independent cell.

[0045] The profile acquisition unit (110) may be configured to acquire one or more profiles based on the voltage and capacity of the battery.

[0046] Specifically, any profile related to the voltage and capacity of a battery can be acquired without limitation on its type. For example, profiles based on the voltage and capacity of a battery, such as battery profiles and differential profiles, can be acquired.

[0047] A battery profile is a profile that represents the relationship between voltage (V) and capacity (Q) when the battery's SOC is charged from a preset start SOC or 0% to a preset end SOC or 100%. Alternatively, a battery profile may represent the relationship between voltage (V) and capacity (Q) when the battery's SOC is discharged from a preset start SOC or 100% to a preset end SOC or 0%.

[0048] A differential profile may include a differential capacity profile and a differential voltage profile. The differential capacity profile is a profile obtained by differentiating the battery profile with respect to voltage, and represents a relationship between the differential capacity (dQ / dV) and voltage (V). The differential voltage profile is a profile obtained by differentiating the battery profile with respect to capacity, and represents a relationship between the differential voltage (dV / dQ) and capacity (Q).

[0049] For example, there are no specific restrictions on the C-rate for charging or discharging to generate a battery profile. However, to obtain more accurate battery profiles and differential profiles, it is desirable to charge or discharge the battery at a low rate. For example, a battery profile can be generated during the process of charging or discharging the battery at 0.05C.

[0050] For example, the profile acquisition unit (110) can directly receive a profile for a battery from the outside. That is, the profile acquisition unit (110) can acquire a profile for a battery by receiving a profile through a wired and / or wireless connection to the outside.

[0051] As another example, the profile acquisition unit (110) may receive battery information regarding the voltage and capacity of the battery. Furthermore, the profile acquisition unit (110) may generate a profile for the battery based on the received battery information. In other words, the profile acquisition unit (110) may acquire a profile for the battery by directly generating a profile based on the battery information.

[0052] FIG. 2 is a schematic diagram illustrating a plurality of profiles according to one embodiment of the present invention. Here, the profile is a differential voltage profile indicating a correspondence between a capacity and a differential voltage. In addition, the profile can be expressed as an XY graph in which the X-axis is set to the capacity (Q) and the Y-axis is set to the differential voltage (dV / dQ).

[0053] In the embodiment of FIG. 2, the profile acquisition unit (110) can acquire a first profile (P1), a second profile (P2), a third profile (P3), and a fourth profile (P4).

[0054] The profile acquisition unit (110) may be connected to the image conversion unit (120) so as to be able to communicate with it. For example, the profile acquisition unit (110) may be connected to the image conversion unit (120) by wire and / or wirelessly. The profile acquisition unit may transmit one or more acquired profiles to the image conversion unit (120).

[0055] The image conversion unit (120) may be configured to convert each of one or more profiles into an image and generate a diagnostic image from the converted one or more images.

[0056] Specifically, the image conversion unit (120) can convert a profile into an image. For example, in the embodiment of FIG. 2, each of the first profile (P1), the second profile (P2), the third profile (P3), and the fourth profile (P4) can be converted into an image. That is, the image conversion unit (120) can generate a total of four images.

[0057] In the embodiment of Fig. 2, the profile is expressed as an XY graph, but the profile may also be in the form of a table listing battery information for the measurement point in time. In this case, the image conversion unit (120) can convert the profile into an XY graph and then convert the profile expressed as an XY graph into an image.

[0058] In addition, the image conversion unit (120) can be configured to generate a diagnostic image by synthesizing one or more images.

[0059] Preferably, one or more profiles acquired by the profile acquisition unit (110) may have the same axis scale. Specifically, an axis scale corresponding to each of the battery profile, differential voltage profile, or differential capacity profile may be preset.

[0060] Since one or more images generated by the image conversion unit (120) have the same axis scale, the image conversion unit (120) can generate a diagnostic image by synthesizing one or more generated images. Specifically, the image conversion unit (120) can generate a diagnostic image by overlapping one or more generated images.

[0061] The control unit (130) can be configured to diagnose the state of a battery corresponding to a diagnostic image using a pre-learned diagnostic model.

[0062] The diagnostic model can be trained to determine the battery condition from diagnostic images using preset training data. Any diagnostic model capable of learning and analyzing input diagnostic images based on the training results can be applied without limitation. For example, the diagnostic model can be configured as an artificial neural network (ANN) based on deep learning. Specifically, the diagnostic model may include a convolutional neural network (CNN), a recurrent neural network (RNN), a transformer, or a hybrid model based on these.

[0063] Furthermore, the learning data is preset as profiles for multiple reference batteries, and the states of the multiple reference batteries may vary. Preferably, the learning data may also be images of the profiles. For example, profiles for reference batteries in various states, such as sudden drop occurrence, lithium plating occurrence, positive electrode capacity loss, negative electrode capacity loss, internal gas generation, venting, fire occurrence, internal short circuit occurrence, and electrode lead (or electrode tab) disconnection, may be preset as learning data. Accordingly, the diagnostic model can analyze the diagnostic images and output the state with the highest probability among the learned states as the state of the battery.

[0064] The control unit (130) can input the diagnostic image generated by the image conversion unit (120) into the diagnostic model. Then, the control unit (130) can obtain the result output from the diagnostic model and diagnose the state of the battery based on the obtained result.

[0065] Preferably, the learning data may be preset as images of profiles for the entire life cycle of each of the plurality of reference batteries. For example, for each of the plurality of reference batteries, at least one of a cycle-specific image, a composite image for some cycles, and a composite image for the entire cycle may be set as learning data. Accordingly, the control unit (130) can diagnose the past state, current state, and / or future state of the battery using the diagnostic model. For example, the control unit (130) can diagnose the state of the battery in the past, the current state of the battery, and the state of the battery in the future.

[0066] For example, in the embodiment of FIG. 2, the control unit (130) can input diagnostic images based on multiple profiles (P1, P2, P3, P4) into the diagnostic model. The control unit (130) can diagnose the past and present states of the battery as normal based on the results output from the diagnostic model. However, the control unit (130) can diagnose the future state of the battery as a sudden drop occurrence state.

[0067] Since the battery diagnosis device (100) according to one embodiment of the present invention diagnoses the state of the battery through an image, it has the advantage of being able to quickly diagnose the state of the battery using an image of the battery profile.

[0068] Furthermore, the battery diagnostic device (100) can not only track and diagnose the battery's condition from the past to the present, but can also predict its future condition. Because it can track the condition of the battery throughout its entire life cycle, the battery diagnostic device (100) can detect potential battery problems in advance. Accordingly, by appropriately setting battery usage conditions based on the diagnostic results obtained by the battery diagnostic device (100), the expected battery lifespan can be dramatically increased.

[0069]

[0070] Meanwhile, the profile acquisition unit (110), image conversion unit (120), and control unit (130) provided in the battery diagnosis device (100) may optionally include a processor, an application-specific integrated circuit (ASIC), another chipset, a logic circuit, a register, a communication modem, a data processing device, etc. known in the art to execute various control logics performed in the present invention. In addition, when the control logic is implemented in software, the profile acquisition unit (110), the image conversion unit (120), and the control unit (130) may be implemented as a set of program modules.

[0071] In addition, the battery diagnostic device (100) may further include a storage unit (140). The storage unit (140) may store data or programs required for each component of the battery diagnostic device (100) to perform operations and functions, or data generated in the process of performing operations and functions. The storage unit (140) is not particularly limited in type as long as it is a known information storage means known to be able to record, erase, update, and read data. As an example, the information storage means may include a random access memory (RAM), a flash memory, a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a register, etc. In addition, the storage unit (140) may store program codes defining processes executable by the profile acquisition unit (110), the image conversion unit (120), and the control unit (130).

[0072] For example, the storage unit (140) can store one or more profiles, diagnostic images, diagnostic models, etc. acquired by the profile acquisition unit (110).

[0073]

[0074] The image conversion unit (120) may be configured to convert a profile for a cycle less than or equal to a preset reference cycle corresponding to a target cycle among one or more profiles into an image.

[0075] Specifically, the image conversion unit (120) may not convert all profiles acquired by the profile acquisition unit (110) into images, but may only convert a number of profiles corresponding to the target cycle into images. Here, since a reference cycle corresponding to the target cycle is preset, the image conversion unit (120) may only convert profiles for cycles less than or equal to the reference cycle into images.

[0076] For example, it is assumed that the profile acquisition unit (110) has acquired profiles from the 1st cycle to the 100th cycle, the target cycle is the 200th cycle, and the reference cycle corresponding to the target cycle is the 50th cycle. The image conversion unit (120) may not convert all 100 profiles (the 1st to the 100th cycles) into images, but may convert 50 profiles (the 1st to the 50th cycles) into images. That is, the remaining 50 profiles (the 51st to the 100th cycles) may not be converted into images.

[0077] The reference cycle can be preset as a cycle whose verification result accuracy for the target cycle exceeds a preset reference value during the verification process of the diagnostic model against preset verification data. Preferably, the cycle with the lowest accuracy among multiple cycles whose verification results exceed the reference value can be preset as the reference cycle.

[0078] Specifically, the validation process for multiple validation batteries was conducted, with the number of cycles used to validate the diagnostic model increasing by n (where n is a natural number). Note that the validation battery differs from the reference battery, and information about the validation battery is not included in the diagnostic model's training data.

[0079] In each verification process, images of the profiles of multiple verification batteries were synthesized to create a verification image, which was then input into the diagnostic model. The synthesized profiles were profiles for the cycles corresponding to each verification process. The verification process then calculated accuracy by comparing the actual condition of the verification battery during the target cycle with the diagnostic model's diagnostic results.

[0080] Figure 3 is a schematic diagram illustrating the verification results of a diagnostic model according to one embodiment of the present invention. Specifically, the embodiment of Figure 3 shows the verification results of the diagnostic model for the target cycle (the 200th cycle) of multiple verification batteries. The verification process was performed a total of 10 times, increasing the number of cycles by 10 each time.

[0081] In the embodiment of Fig. 3, the accuracy corresponding to the first to tenth cycles is a10(%). That is, the diagnostic accuracy of the diagnostic model for the verification images of each of the plurality of verification batteries is a10(%). Here, the verification images are images obtained by synthesizing the profile images corresponding to the first to tenth cycles, each for each of the plurality of verification batteries.

[0082] Next, the accuracy corresponding to the 1st to 20th cycles is a20(%), the accuracy corresponding to the 1st to 50th cycles is a50(%), and the accuracy corresponding to the 1st to 100th cycles is a100(%).

[0083] Specifically, in the 10 verification processes, the cycles whose accuracy is higher than the reference accuracy are the 50th to 100th cycles. That is, the verification accuracy of the 1st to 50th cycles, the 1st to 60th cycles, the 1st to 70th cycles, the 1st to 80th cycles, the 1st to 90th cycles, and the 1st to 100th cycles is higher than the reference value.

[0084] Finally, since the accuracy is above the reference value and the lowest cycle is the 50th cycle, the 50th cycle can be set as the reference cycle for the target cycle (the 200th cycle).

[0085] And, when the target cycle is set to the 200th cycle during the diagnosis process, the image conversion unit (120) can convert the profile corresponding to the 1st to 50th cycles into an image and create a diagnostic image using the converted images.

[0086] The control unit (130) can be configured to diagnose the state of the battery corresponding to the target cycle from the diagnostic image using the diagnostic model.

[0087] Specifically, the control unit (130) can diagnose the state of the battery in a target cycle using a diagnostic image. If the target cycle is a future cycle of the battery, the state of the battery in the target cycle can be predicted and diagnosed.

[0088]

[0089] The diagnostic model can be configured to generate a diagnostic result image that displays key areas considered in determining the condition of the battery across the entire area of ​​the diagnostic image.

[0090] Here, the key region is the area where the diagnostic model intensively analyzes diagnostic images to determine the battery's condition. This may be one or more regions. These key regions can be determined based on learning results for the reference battery.

[0091] For example, if there is a specific pattern in the profile of a reference battery that experiences sudden drops, this specific pattern can be learned. The diagnostic model can then consider areas where this specific pattern is likely to appear as key areas to determine whether the diagnostic image contains this specific pattern.

[0092] Figures 4 to 7 are schematic diagrams illustrating diagnostic result images according to one embodiment of the present invention.

[0093] In the embodiments of FIGS. 4 to 7, the diagnostic result image may display a first region (S1), a second region (S2), a third region (S3), and a fourth region (S4). While this embodiment describes four regions displayed in the diagnostic result image, the regions may be further subdivided depending on the learning data and learning design.

[0094] The diagnostic model can be configured to further indicate the importance of key regions in the diagnostic result image.

[0095] Specifically, the diagnostic model can determine the importance of each key area and display the determined importance on the diagnostic results image. For example, importance can be displayed as a number, symbol, or heat map.

[0096] For example, the diagnostic model may be a CNN with gradient-weighted class activation mapping (Grad-CAM) or Grad-CAM++ applied. Here, Grad-CAM can indicate which parts of the diagnostic image influenced the CNN's final classification decision (battery condition determination).

[0097] Preferably, the entire area of ​​the diagnostic image can be considered for battery condition diagnosis. However, the diagnostic model can be configured to mark areas within the entire diagnostic image whose importance exceeds a preset threshold as key areas. In other words, the diagnostic result image can display the key areas considered most important for diagnosing the battery condition and their importance levels. Therefore, the user can easily identify battery specific characteristics through the diagnostic result image.

[0098] For example, in the embodiments of FIGS. 4 to 7, importance may be displayed for each of a plurality of key areas (S1, S2, S3, S4). In this embodiment, importance is displayed in a heatmap format, but any means capable of displaying importance may be applied without limitation.

[0099]

[0100] The control unit (130) may be configured to diagnose the cause of the battery condition as any one of a plurality of preset reference causes.

[0101] Specifically, the control unit (130) can diagnose the battery condition for a target cycle using a diagnostic model. Furthermore, the control unit (130) can further diagnose the cause of the battery condition based on the diagnostic result image. That is, since the diagnostic result image displays key areas, the control unit (130) can diagnose the cause of the battery condition from the diagnostic result image.

[0102] For example, multiple reference causes may include cathodic degeneration dominance, anodic degeneration dominance, and balanced degeneration. Here, cathodic degeneration dominance refers to the cathode being more degenerated than the anode, indicating a disruption in the degeneration balance between the anode and cathode. Conversely, anodic degeneration dominance refers to the anode being more degenerated than the cathode, indicating a disruption in the degeneration balance between the anode and cathode. Furthermore, balanced degeneration refers to a balanced degeneration of the anode and cathode.

[0103] Additionally, the control unit (130) can be configured to set the usage conditions of the battery in response to the diagnosis results.

[0104] For example, if the cause of the battery condition is diagnosed as a negative electrode degradation condition, the control unit (130) may reduce the upper charge limit C-rate to prevent the negative electrode from degrading more than the positive electrode. In the embodiment of FIG. 4, the control unit (130) may diagnose the cause of sudden death as a negative electrode degradation condition and reduce the upper charge limit C-rate set for the battery.

[0105] As another example, if the cause of the battery condition is diagnosed as a positive electrode deterioration state, the control unit (130) can reduce the upper limit charge voltage to prevent the positive electrode from deteriorating further than the negative electrode. In the embodiments of FIGS. 5 and 6, the control unit (130) can diagnose the cause of sudden death as a positive electrode deterioration state and reduce the upper limit charge voltage set for the battery. In addition, in the embodiment of FIG. 6, since the importance of the third main region (S3) is high, the upper limit charge C-rate can be reduced in the capacity section corresponding to the third main region (S3) to prevent further degradation in the third main region (S3).

[0106] As another example, if the cause of the battery condition is diagnosed as a balanced degradation state, the upper charge limit C-rate and upper charge limit voltage can be reduced. In the embodiment of FIG. 7, the control unit (130) can diagnose the cause of sudden death as a positive electrode degradation state and reduce the upper charge limit C-rate and upper charge limit voltage set for the battery.

[0107] The battery diagnostic device (100) can diagnose the condition and cause of the condition of the battery, and set the battery usage conditions corresponding to the diagnosis results. That is, according to the battery diagnostic device (100), the expected lifespan of the battery can be increased, and unexpected accidents can be prevented in advance.

[0108]

[0109] The battery diagnosis device (100) according to the present invention can be applied to a BMS (Battery Management System). That is, the BMS according to the present invention can include the battery diagnosis device (100) described above. In this configuration, at least some of the components of the battery diagnosis device (100) can be implemented by supplementing or adding to the functions of the components included in a conventional BMS. For example, the profile acquisition unit (110), image conversion unit (120), control unit (130), and storage unit (140) of the battery diagnosis device (100) can be implemented as components of the BMS.

[0110] In addition, the battery diagnostic device (100) according to the present invention may be installed in a battery pack. That is, the battery pack according to the present invention may include the battery diagnostic device (100) described above and one or more battery cells. In addition, the battery pack may further include electrical components (relays, fuses, etc.) and a case, etc.

[0111] FIG. 8 is a schematic drawing of a battery pack (10) according to another embodiment of the present invention.

[0112] The positive terminal of the battery (11) can be connected to the positive terminal (P+) of the battery pack (10), and the negative terminal of the battery (11) can be connected to the negative terminal (P-) of the battery pack (10).

[0113] The measuring unit (12) can be connected to a first sensing line (SL1), a second sensing line (SL2), and a third sensing line (SL3). Specifically, the measuring unit (12) can be connected to a positive terminal of the battery (11) through the first sensing line (SL1), and can be connected to a negative terminal of the battery (11) through the second sensing line (SL2). The measuring unit (12) can measure the voltage of the battery (11) based on the voltage measured at each of the first sensing line (SL1) and the second sensing line (SL2).

[0114] And, the measuring unit (12) can be connected to the current measuring unit (A) through the third sensing line (SL3). For example, the current measuring unit (A) can be an ammeter or a shunt resistor capable of measuring the charging current and discharging current of the battery (11). The measuring unit (12) can measure the charging current of the battery (11) through the third sensing line (SL3) to calculate the charging amount. In addition, the measuring unit (12) can measure the discharging current of the battery (11) through the third sensing line (SL3) to calculate the discharging amount.

[0115] For example, the profile acquisition unit (110) can receive battery information about the voltage and current of the battery from the measurement unit (12). Then, the profile acquisition unit (110) can generate a profile based on the battery information.

[0116] As another example, the profile acquisition unit (110) can receive a profile from the measurement unit (12).

[0117] An external device may be connected to the positive terminal (P+) and negative terminal (P-) of the battery pack (10). For example, the external device may be a charging device or a load. In addition, the positive terminal of the battery (11), the positive terminal (P+) of the battery pack (10), the external device, the negative terminal (P-) of the battery pack (10), and the negative terminal of the battery (11) may be electrically connected.

[0118] For example, the battery pack (10) may be included in an automobile, such as an electric vehicle (EV) or a hybrid vehicle (HV). Furthermore, the battery pack (10) may power a motor through an inverter installed in the automobile, thereby driving the automobile.

[0119]

[0120] FIG. 9 is a schematic diagram illustrating a server (1000) according to another embodiment of the present invention.

[0121] Referring to FIG. 9, the server (1000) may include a battery diagnostic device (100), a communication module (1100), and a storage module (1200). In addition, the server (1000) may be configured to be able to communicate with a battery information providing device (2000). For example, the battery information providing device (2000) may be a device capable of providing battery information and / or profiles to the server (1000), and may be a BMS, a charging device, a diagnostic device, or the like.

[0122] The communication module (1100) may be connected to the battery information providing device (2000) to enable communication via wired and / or wireless means. For example, the communication module (1100) may receive battery information and / or a profile from the battery information providing device (2000).

[0123] The battery diagnostic device (100) can be connected to the communication module (1100) to enable communication via a phone line and / or wirelessly. The battery diagnostic device (100) can diagnose the status of the battery by acquiring battery information and / or profiles received by the communication module (1100).

[0124] The storage module (1200) can store battery information and / or profiles received by the communication module (1100). In addition, the storage module (1200) can store diagnostic images, diagnostic result images, and diagnostic models used to diagnose the status of the battery.

[0125] Preferably, the server (1000) is connected to enable communication with a plurality of battery information providing devices, and can diagnose the status of a corresponding battery based on data received from each of the plurality of battery information providing devices.

[0126]

[0127] FIG. 10 is a diagram schematically illustrating a battery diagnosis method according to another embodiment of the present invention.

[0128] Referring to FIG. 10, the battery diagnosis method may include a profile acquisition step (S100), an image conversion step (S200), and a diagnosis step (S300).

[0129] Preferably, each step of the battery diagnosis method can be performed by the battery diagnosis device (100). In the following, for convenience of explanation, any content that overlaps with the previously described content will be omitted or briefly described.

[0130] The profile acquisition step (S100) is a step of acquiring one or more profiles based on the voltage and capacity of the battery, and can be performed by the profile acquisition unit (110).

[0131] For example, the profile acquisition unit (110) can directly receive a profile for a battery from the outside. That is, the profile acquisition unit (110) can acquire a profile for a battery by receiving a profile through a wired and / or wireless connection to the outside.

[0132] As another example, the profile acquisition unit (110) may receive battery information regarding the voltage and capacity of the battery. Furthermore, the profile acquisition unit (110) may generate a profile for the battery based on the received battery information. In other words, the profile acquisition unit (110) may acquire a profile for the battery by directly generating a profile based on the battery information.

[0133] The image conversion step (S200) is a step of converting each of one or more profiles into an image and generating a diagnostic image from the converted one or more images, and can be performed by the image conversion unit (120).

[0134] Specifically, the image conversion unit (120) can convert a profile into an image. In addition, the image conversion unit (120) can be configured to synthesize one or more images to generate a diagnostic image.

[0135] The diagnosis step (S300) is a step of diagnosing the state of a battery corresponding to a diagnosis image using a pre-learned diagnosis model, and can be performed by the control unit (130).

[0136] The control unit (130) can input the diagnostic image generated by the image conversion unit (120) into the diagnostic model. Then, the control unit (130) can obtain the result output from the diagnostic model and diagnose the state of the battery based on the obtained result.

[0137] Furthermore, the control unit (130) can further diagnose the cause of the battery condition based on the diagnosis result image. That is, since the diagnosis result image displays key areas, the control unit (130) can diagnose the cause of the battery condition from the diagnosis result image.

[0138]

[0139] The embodiments of the present invention described above are not implemented only through devices and methods, but may also be implemented through a program that realizes a function corresponding to the configuration of the embodiments of the present invention or a recording medium on which the program is recorded, and such implementation can be easily implemented by an expert in the technical field to which the present invention belongs based on the description of the embodiments described above.

[0140] Although the present invention has been described above with reference to limited embodiments and drawings, the present invention is not limited thereto, and it is obvious that various modifications and variations are possible within the scope of the technical idea of ​​the present invention and the equivalent scope of the patent claims to be described below by a person having ordinary skill in the art to which the present invention pertains.

[0141] In addition, the present invention described above is not limited to the above-described embodiments and the attached drawings, and all or part of each embodiment may be selectively combined and configured so that various modifications can be made, as those skilled in the art can make various substitutions, modifications, and changes within the scope of the technical idea of ​​the present invention.

[0142]

[0143] (Explanation of symbols)

[0144] 10: Battery pack

[0145] 11: Battery

[0146] 12: Measurement section

[0147] 100: Battery Diagnostic Device

[0148] 110: Profile acquisition section

[0149] 120: Image conversion unit

[0150] 130: Control unit

[0151] 130: Storage

[0152] 1000: Server

[0153] 1100: Communication Module

[0154] 1200: Storage Module

[0155] 2000: Battery Information Provider

Claims

1. A profile acquisition unit configured to acquire one or more profiles based on the voltage and capacity of the battery; An image conversion unit configured to convert each of the one or more profiles into an image and generate a diagnostic image from the converted one or more images; and A battery diagnosis device characterized by including a control unit configured to diagnose the state of the battery corresponding to the diagnostic image using a pre-learned diagnostic model.

2. In paragraph 1, The above diagnostic model is, A battery diagnosis device characterized in that it is trained to determine the state of the battery from the diagnostic image through preset learning data.

3. In paragraph 1, The above control unit, A battery diagnosis device characterized in that it is configured to diagnose the state of the battery corresponding to the target cycle from the diagnostic image using the diagnostic model.

4. In paragraph 3, The above image conversion unit, A battery diagnostic device characterized in that it is configured to convert a profile for a cycle less than or equal to a preset reference cycle corresponding to the target cycle among the one or more profiles into an image.

5. In paragraph 4, The above reference cycle is, A battery diagnostic device characterized in that, in the verification process of the diagnostic model for preset verification data, the accuracy of the verification result for the target cycle is preset to a cycle greater than or equal to a preset reference value.

6. In paragraph 5, The above reference cycle is, A battery diagnostic device characterized in that the accuracy of the verification result is preset to the lowest cycle among a plurality of cycles having a value higher than the reference value.

7. In paragraph 1, The above diagnostic model is, A battery diagnostic device characterized in that it is configured to generate a diagnostic result image that displays a major area considered in determining the condition of the battery in the entire area of the diagnostic image.

8. In paragraph 7, The above diagnostic model is, A battery diagnostic device characterized in that it is configured to further display the importance of the major area in the above diagnostic result image.

9. In paragraph 8, The above diagnostic model is, A battery diagnostic device characterized in that it is configured to display an area in the entire area of the diagnostic image in which the importance is greater than a preset threshold as the main area.

10. In paragraph 1, The above control unit, A battery diagnosis device characterized in that it is configured to diagnose the cause of the state of the battery as one of a plurality of preset reference causes and to set the usage conditions of the battery corresponding to the diagnosis result.

11. In paragraph 1, The above image conversion unit, A battery diagnostic device characterized in that it is configured to generate the diagnostic image by synthesizing one or more of the above images.

12. A battery pack comprising a battery diagnostic device according to any one of claims 1 to 11.

13. A server including a battery diagnostic device according to any one of claims 1 to 11.

14. A profile acquisition step for acquiring one or more profiles based on the voltage and capacity of the battery; An image conversion step of converting each of the one or more profiles into an image and generating a diagnostic image from the converted one or more images; and A battery diagnosis method, characterized by including a diagnosis step of diagnosing the state of the battery corresponding to the diagnosis image using a pre-learned diagnosis model.

Images