Method and apparatus for estimating the capacity of a battery installed in a vehicle

Abstract

The present disclosure relates to a method and apparatus for estimating the capacity of a battery mounted in a vehicle. According to one embodiment of the present disclosure, a method for estimating the capacity of a battery mounted in a vehicle may be provided, comprising: a step of acquiring time series data for a battery pack mounted in a vehicle and supplying power to a motor of the vehicle; and a step of calculating a first estimated remaining capacity of the battery pack at a first time point based on the time series data and a correction weight, wherein the correction weight is set based on state information including the total driving distance of the vehicle.

Description

Technology Field

[0001] The present disclosure relates to a method and apparatus for estimating the capacity of a battery mounted in a vehicle. Background Technology

[0002] Automobiles using internal combustion engines that use gasoline or heavy fuel oil as primary fuel contribute to pollution, such as air pollution. Recently, significant efforts have been devoted to the development of electric vehicles or hybrid vehicles to reduce pollution.

[0003] An electric vehicle is a vehicle that uses a battery engine powered by electrical energy output from a battery. Since such electric vehicles use a battery formed by a pack of multiple rechargeable secondary cells as a power source, they have the advantage of producing no exhaust gas and having low noise.

[0004] Meanwhile, a hybrid vehicle is a vehicle that falls between an internal combustion engine vehicle and an electric vehicle, and is a vehicle that uses two or more power sources, such as an internal combustion engine and a battery engine. Currently, hybrid vehicles are being developed in mixed forms, such as those using an internal combustion engine and a fuel cell that generates direct electrical energy by causing a chemical reaction while continuously supplying hydrogen and oxygen, or those using a battery and a fuel cell.

[0005] Conventional technology for estimating the State of Charge (SoC) of a battery has used a method of pre-determining the relationship between the remaining capacity and factors such as current integration, open-circuit voltage, discharge voltage, internal resistance, temperature, and discharge current, and estimating the remaining capacity corresponding to the detected factor by detecting at least one factor.

[0006] Since the remaining capacity estimation method according to conventional technology frequently experiences errors, the inaccurate prediction of driving range not only causes user inconvenience and reduced reliability, but also leads to inefficient management of the battery management system and an increased risk of safety accidents.

[0007] The aforementioned background technology is technical information that the inventor possessed for the derivation of the present invention or acquired during the process of deriving the present invention, and it cannot be considered as prior art disclosed to the general public prior to the filing of the present invention. The problem to be solved

[0008] The present disclosure provides a method and apparatus for estimating the capacity of a battery mounted in a vehicle. The problems to be solved by the present disclosure are not limited to those mentioned above, and other problems and advantages of the present disclosure not mentioned can be understood from the following description and will be more clearly understood from the embodiments of the present disclosure. Furthermore, it will be understood that the problems and advantages to be solved by the present disclosure can be realized by the means and combinations thereof set forth in the claims. means of solving the problem

[0009] As a technical means for achieving the aforementioned technical problem, a first aspect of the present disclosure may provide a method for estimating the capacity of a battery mounted on a vehicle, comprising: a step of acquiring time series data for a battery pack mounted on a vehicle and supplying power to a motor of said vehicle; and a step of calculating a first estimated remaining capacity of said battery pack at a first time point based on said time series data and a correction weight, wherein the correction weight is set based on state information including the total driving distance of said vehicle.

[0010] A second aspect of the present disclosure may provide an apparatus for estimating the capacity of a battery mounted on a vehicle, comprising: a communication module; a memory storing at least one program; and a processor operating by executing said at least one program, wherein the processor controls the communication module to acquire time-series data for a battery pack mounted on a vehicle and supplying power to a motor of said vehicle, and calculates a first estimated remaining capacity of said battery pack at a first time point based on said time-series data and a correction weight, and said correction weight is set based on state information including the total driving distance of said vehicle.

[0011] A third aspect of the present disclosure may provide a computer-readable non-transient recording medium that records a program for executing the method of the first aspect of the present disclosure on a computer.

[0012] Other aspects, features, and advantages other than those described above will become clear from the following drawings, claims, and detailed description of the invention. Effects of the invention

[0013] According to the means for solving the problem of the present disclosure described above, by generating an estimated remaining capacity using a correction weight, the remaining capacity of a battery pack at a specific point in time can be estimated with high accuracy for a vehicle operating in an actual usage environment.

[0014] The effects of the embodiments of the present disclosure are not limited to the effects mentioned above, and other unmentioned effects will be clearly understood by those skilled in the art from the description in this specification. Brief explanation of the drawing

[0015] The following drawings attached to this specification are intended to illustrate at least one embodiment according to the present disclosure and serve to further enhance understanding of the technical concept of the present invention together with the detailed description of the invention set forth below; therefore, the present disclosure should not be interpreted as being limited only to the matters described in the drawings. Figure 1 is an example of a system including an estimation device. Figure 2 is a graph showing the measured stored energy of a battery pack. Figure 3 is an example of how an estimation device operates. FIG. 4 is an exemplary drawing for explaining the process of calculating a first estimated remaining capacity according to one embodiment. FIG. 5 is an exemplary diagram illustrating a correction weight including a plurality of weights set for each remaining capacity interval. Figure 6 is a graph showing the current measurement values ​​of the battery pack. FIG. 7 is an exemplary diagram illustrating the process of calculating a predetermined remaining capacity change amount for a predetermined time interval. Figure 8 is an exemplary diagram illustrating the process of generating correction weights based on state information using a previously trained prediction model. FIG. 9 is a block diagram of an estimation device according to one embodiment. Specific details for implementing the invention

[0016] The advantages and features of the present disclosure and the methods for achieving them will become clear by referring to the embodiments described in detail together with the accompanying drawings. However, the present disclosure is not limited to the embodiments presented below, but can be implemented in various different forms and should be understood to include all modifications, equivalents, and substitutions that fall within the spirit and scope of the present disclosure. The embodiments presented below are provided to make the present disclosure complete and to fully inform those skilled in the art of the scope of the invention. In describing the present disclosure, detailed descriptions of related prior art are omitted where it is determined that such detailed descriptions may obscure the essence of the present invention.

[0017] The terms used herein are used merely to describe specific embodiments and are not intended to limit the disclosure. Unless otherwise defined, all terms used herein have the same meaning as generally understood by those skilled in the art to which this disclosure pertains.

[0018] In this specification, singular expressions include plural expressions unless the context clearly indicates otherwise. Furthermore, terms such as "comprising" or "having" are intended to specify the existence of the features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, and should be understood as not precluding the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.

[0019] Additionally, terms including ordinal numbers, such as "first" or "second" as used herein, may be used to describe various components, but the components should not be limited by the terms. The terms are used solely for the purpose of distinguishing one component from another.

[0020] Phrases such as "in one embodiment," "according to one embodiment," "related to one embodiment," or "according to an implementation of one embodiment" in this specification do not necessarily refer to the same embodiment. Furthermore, throughout this specification, "examples" are arbitrary distinctions to facilitate the description of the present disclosure, and each embodiment does not need to be mutually exclusive. For example, configurations mentioned for the description of one embodiment may be applied and / or implemented in other embodiments, and may be modified and applied and / or implemented to the extent that they do not depart from the scope of the present disclosure.

[0021] Some embodiments of the present disclosure may be represented by functional block configurations and various processing steps. Some or all of these functional blocks may be implemented by various numbers of hardware and / or software configurations that perform specific functions. For example, the functional blocks of the present disclosure may be implemented by one or more microprocessors or by circuit configurations for a specific function.

[0022] For example, the functional blocks of the present disclosure may be implemented in various programming or scripting languages. The functional blocks may be implemented as algorithms executed on one or more processors. Additionally, the present disclosure may employ prior art for electronic configuration, signal processing, and / or data processing, etc. Terms such as "mechanism," "element," "means," and "configuration" may be used broadly and are not limited to mechanical and physical configurations. Furthermore, terms such as "-part," "-module," etc. refer to a unit that processes at least one function or operation, which may be implemented in hardware or software, or as a combination of hardware and software.

[0023] Furthermore, the connecting lines or connecting members between the components depicted in the drawings are merely illustrative of functional connections and / or physical or circuit connections. In the actual device, connections between components may be represented by various alternative or added functional connections, physical connections, or circuit connections.

[0024] Additionally, some components in the drawings may be depicted with slightly exaggerated sizes or proportions. Furthermore, components depicted in one drawing may not be depicted in another drawing.

[0025] The present disclosure will be described in detail below with reference to the attached drawings.

[0026] Figure 1 is an example of a system including an estimation device.

[0027] Referring to FIG. 1, a system (100) according to one embodiment may include an estimation device (110) and a vehicle (120).

[0028] In the present disclosure, a vehicle (120) may refer to any type of means of transportation used to move people or goods with an engine, such as an automobile, bus, motorcycle, kickboard, or truck. A vehicle (120) according to one embodiment may be equipped with a battery pack as a power source for the vehicle (120). For example, the vehicle (120) may be equipped with a battery pack that supplies power to the motor of the vehicle (120). Additionally, the battery pack may include a plurality of battery cells capable of charging and discharging.

[0029] In the present disclosure, the estimation device (110) may refer to a device for estimating the battery state of a battery pack mounted on a vehicle (120). In one embodiment, the battery state may include the remaining capacity (SoC) of the battery pack. In this case, the remaining capacity may refer to the charging state at a specific point in time and may be expressed as the current level of charging relative to the maximum capacity of the battery.

[0030] In one embodiment, the estimation device (110) may be implemented as a device mounted on a vehicle (120) to estimate the battery state of a battery pack, a server device for managing the battery pack, a device portable by a user operating or managing the vehicle, or a combination of at least some of these. For example, the estimation device (110) may be implemented as a computing device mounted on the vehicle along with the battery pack, such as a battery management system (BMS), a server device of an entity supplying or managing the battery pack, a smartphone, tablet PC, GPS (global positioning system) device, or other mobile or non-mobile computing device of a user operating or managing the vehicle, but is not limited thereto.

[0031] In one embodiment, the estimation device (110) may acquire time-series data for a battery pack. For example, the time-series data may include, but is not limited to, voltage data, current data, temperature data and / or resistance data of the battery pack as data recorded over time.

[0032] In one embodiment, time-series data for a battery pack may be collected through at least one sensor provided in the vehicle (120), and said at least one sensor may be provided inside the battery pack or electrically connected to the battery pack and used in the process of collecting time-series data for the battery pack. For example, the at least one sensor provided in the vehicle (120) may include, but is not limited to, a current sensor, a voltage sensor, and / or a temperature sensor.

[0033] In one embodiment, the estimation device (110) may obtain time series data from at least one sensor used in the process of collecting time series data, or from a separate storage device that stores time series data collected through at least one sensor. In one embodiment, the storage device that stores time series data and provides it to the estimation device (110) may include a storage device of a battery management system (BMS) that manages a battery pack mounted on a vehicle (120).

[0034] In one embodiment, the estimation device (110) can calculate the estimated remaining capacity of the battery pack of the vehicle (120) based on time series data for the battery pack of the vehicle (120). For example, the estimation device (110) can calculate the estimated remaining capacity of the battery pack at a predetermined point in time based on time series data and correction weights. Through this, the estimated remaining capacity of the battery pack at a predetermined point in time can be calculated for the vehicle (120) operating in an actual usage environment.

[0035] Meanwhile, it is impossible or very difficult to verify the chemical state inside a battery in a real-world operating environment. According to conventional technology, there are difficulties in precisely monitoring the maximum capacity of a battery that decreases with vehicle operation in a real-world operating environment, and when the estimated remaining capacity is calculated using only time-series data of the battery pack via indirect means, errors frequently occur, such as the estimated remaining capacity falling outside the 0-100% range.

[0036] In particular, vehicles are frequently exposed to the external environment and the external environment in which they operate is highly diverse. Furthermore, since vehicle batteries have a relatively longer replacement cycle than small electronic devices, it is difficult to accurately predict the intrinsic characteristics of vehicle batteries (e.g., maximum battery capacity) that may change over time.

[0037] In one embodiment, a correction weight may be used to solve the aforementioned problem. For example, the correction weight may include at least one weight for correcting time series data or for correcting data derived based on time series data. By using the correction weight, the battery state of the battery pack can be estimated with high accuracy even in a real-world usage environment where the battery pack is mounted in a vehicle.

[0038] Meanwhile, the specific process for calculating the estimated remaining capacity of a battery pack at a given point in time based on time series data and correction weights will be described later with reference to FIGS. 3 to 8, etc.

[0039] In one embodiment, the system (100) may further include a plurality of vehicles (130). In this case, information regarding a battery pack corresponding to each of the vehicles (130) may be collected through at least one sensor provided in each of the plurality of vehicles (130). For example, each of the plurality of vehicles (130) may be equipped with a battery management system that manages the battery pack mounted in the vehicle (130), and the battery management system may collect information regarding the battery pack to be managed.

[0040] In one embodiment, information regarding a battery pack mounted on a vehicle (130) may include time-series data such as the voltage, current, and temperature of the battery pack, charge / discharge history data such as the charge / discharge cycle of the battery pack, environmental data such as the history of external temperature changes of the vehicle (130), and driving history data such as driving and idle status.

[0041] In one embodiment, a database for setting correction weights may be constructed based on information regarding battery packs corresponding to each of a plurality of vehicles (130). Subsequently, the estimation device (110) may set correction weights corresponding to the vehicles (120) using the constructed database, and may calculate an estimated remaining capacity using time series data of the battery packs mounted on the vehicles (120) and the set correction weights.

[0042] In one embodiment, the entity that collects information regarding battery packs corresponding to each of a plurality of vehicles (130) and performs database construction and data preprocessing may be implemented as the same device as the estimation device (110). In another embodiment, the entity that collects information regarding battery packs corresponding to each of a plurality of vehicles (130) and performs database construction and data preprocessing may be implemented as a separate computing device distinct from the estimation device (110).

[0043] In one embodiment, the estimation device (110), the vehicle (120, 130), and other external devices (e.g., an entity that collects information regarding the battery pack to build a database and perform data preprocessing) can exchange data with each other by communicating using a network. At this time, the network is a data communication network in a comprehensive sense that enables different entities to communicate smoothly with each other, and may include wired internet, wireless internet, and mobile wireless communication networks. For example, the network may include a Local Area Network (LAN), a Wide Area Network (WAN), a Value Added Network (VAN), a mobile radio communication network, a satellite communication network, and combinations thereof.

[0044] For example, wired communication may include, but is not limited to, Ethernet and fiber optic networks. Additionally, for example, wireless communication may include, but is not limited to, Wi-Fi, Bluetooth, Bluetooth Low Energy, ZigBee, Wi-Fi Direct (WFD), ultra-wideband (UWB), infrared data association (IrDA), and near field communication (NFC).

[0045] Meanwhile, components equipped in the vehicle (120, 130) can exchange data with each other by performing communication using a vehicle network. A vehicle network according to one embodiment may include, but is not limited to, LIN (Local Interconnect Network), CAN (Controller Area Network), FlexRay, etc.

[0046] In one embodiment, a battery management system mounted on a vehicle (120, 130) can collect time-series data, such as current data of a battery pack. Subsequently, the vehicle (120, 130) can transmit the time-series data to an estimation device (110) and / or other external device by performing communication using a network.

[0047] Figure 2 is a graph showing the measured stored energy of a battery pack.

[0048] The graph shown in FIG. 2 illustrates the relationship between the remaining capacity estimated according to the prior art and the amount of charging energy calculated through the measured value. In this case, the horizontal axis represents the remaining capacity, and the vertical axis represents the amount of charging energy. In this case, the remaining capacity represents the remaining capacity estimated through an estimation algorithm according to the prior art.

[0049] Referring to FIG. 2, the first line (210) represents the relationship between the remaining capacity and the amount of charging energy corresponding to a vehicle with a driving range of approximately 2000 km, and the second line (220) represents the relationship between the remaining capacity and the amount of charging energy corresponding to a vehicle with a driving range of approximately 12000 km.

[0050] When looking at the second line (220) and the approximate line (230), it can be seen that the slope of the second line (220) changes according to the remaining capacity range, and when comparing the first line (210) and the second line (220), this phenomenon can be understood as occurring as the driving range of the vehicle equipped with the battery increases.

[0051] Meanwhile, the first line (210) and the second line (220) can be understood as examples of information regarding a battery pack mounted on a vehicle (130) as described above with reference to FIG. 1. A correction weight according to one embodiment can be set based on the trend of accumulated information regarding a battery pack mounted on a vehicle (130).

[0052] For example, the database used to set the correction weight may include features of time-series data that appear according to the driving history, driving environment, and / or charging / discharging history of the vehicle (130). As a specific example, the database used to set the correction weight may include features of the remaining capacity-charging energy amount relationship that appears according to the driving distance.

[0053] Figure 3 is an example of how an estimation device operates.

[0054] Referring to FIG. 3, in step 310, the estimation device (110) can acquire time series data for the battery pack. At this time, the acquired time series data may include current data of the battery pack.

[0055] In one embodiment, the battery pack may include a battery pack mounted on a vehicle (120) to supply power to the motor of the vehicle (120).

[0056] In step 320, the estimation device (110) can calculate a first estimated remaining capacity of the battery pack for a first time point based on time series data and correction weights.

[0057] In one embodiment, the correction weight may be set based on state information including the total mileage of the vehicle (120).

[0058] In one embodiment, between the second time point and the first time point, the battery pack may not be fully charged or fully discharged.

[0059] In one embodiment, between the second time point and the first time point, the battery pack may be discharged according to the driving of the vehicle (120) and charged according to the regenerative braking of the vehicle (120).

[0060] In one embodiment, the estimation device (110) can generate correction weights based on state information using a previously learned prediction model and calculate a first estimated remaining capacity based on acquired time series data and generated correction weights.

[0061] FIG. 4 is an exemplary diagram illustrating a process for calculating a first estimated remaining capacity according to one embodiment. That is, steps 410 to 420 shown in FIG. 4 may constitute at least a part of step 320 shown in FIG. 3.

[0062] Referring to FIG. 4, in step 410, the estimation device (110) can calculate the change in remaining capacity per time interval by applying a correction weight to the current integrated value of the current data for at least one time interval. Meanwhile, as described above with reference to FIG. 3, the time series data obtained by the estimation device (110) may include current data of the battery pack.

[0063] In one embodiment, the correction weight may include a plurality of weights set for each remaining capacity interval.

[0064] In one embodiment, the estimation device (110) divides the time between a second time point and a first time point into a plurality of time intervals, and for each of the plurality of time intervals, calculates a predetermined remaining capacity change amount for a predetermined time interval by applying a weight corresponding to a predetermined time interval among a plurality of weights to a current integration value corresponding to a predetermined time interval.

[0065] In one embodiment, the correction weight includes at least one charge correction weight and at least one discharge correction weight, and a plurality of time intervals may each correspond to charging or discharging. At this time, the estimation device (110) can calculate a predetermined remaining capacity change amount by applying a charge correction weight to a current integration value corresponding to a predetermined time interval when a predetermined time interval corresponds to charging, and by applying a discharge correction weight to a current integration value corresponding to a predetermined time interval when a predetermined time interval corresponds to discharging.

[0066] In step 420, the estimation device (110) can calculate the first estimated remaining capacity by accumulating the amount of change in remaining capacity for each time interval between the second time point and the first time point to the second estimated remaining capacity corresponding to the second time point.

[0067] FIG. 5 is an exemplary diagram illustrating a correction weight including a plurality of weights set for each remaining capacity interval.

[0068] Referring to FIG. 5, the estimation device (110) may set a plurality of weights set for each remaining capacity interval as correction weights. In one embodiment, the estimation device (110) may calculate the estimated remaining capacity of the battery pack at a predetermined time point based on time series data for the battery pack mounted on the vehicle (120) and correction weights corresponding to the vehicle (120).

[0069] A correction weight according to one embodiment may include a plurality of weights set for each remaining capacity range. In one embodiment, the remaining capacity may be divided into a plurality of ranges. For example, the remaining capacity range may be divided into a first range (510), a second range (520), and a third range (530), but the number of ranges for which the remaining capacity can be divided is not limited thereto.

[0070] According to measurements based on prior art, such as the measurement results shown in Fig. 2, the degree of correction required may vary depending on the remaining capacity range. Accordingly, in order to reflect the degree of correction required for each remaining capacity range, correction weights may be set for each remaining capacity range.

[0071] The prediction line (501) shown in FIG. 5 represents a linear approximation result for the relationship between the remaining capacity and the amount of charge energy that is predicted to be shown by the measurement of the vehicle (120), that is, the relationship between the remaining capacity and the amount of charge energy that is estimated to appear before the correction weight is applied. At this time, the target line (502) shown in FIG. 5 represents the ideal relationship between the remaining capacity and the amount of charge energy, that is, the relationship between the remaining capacity and the amount of charge energy that is estimated to appear after the correction weight is applied.

[0072] In one embodiment, the number of remaining capacity intervals may be set to a minimum number within a range where the result of the approximation does not exceed the critical error. For example, if the relationship between remaining capacity and charge energy, which is estimated to appear before the correction weight is applied, is approximated by N linear functions corresponding to N intervals, and the error range occurring in at least one of the N intervals exceeds the critical error, and if the error range occurring in each of the N+1 intervals is approximated by N+1 linear functions corresponding to N+1 intervals, and the error range occurring in each of the N+1 intervals does not exceed the critical error, the number of remaining capacity intervals may be set to N+1.

[0073] In one embodiment, the remaining capacity range may be divided into three ranges of 0-35%, 35-65%, and 65-100%, but is not limited thereto.

[0074] In one embodiment, the estimation device (110) can correct the relationship between the remaining capacity and the amount of charging energy that appears along the prediction line (501) when estimating the remaining capacity using only time series data to the relationship between the remaining capacity and the amount of charging energy that appears along the target line (502) by applying a correction weight to the time series data.

[0075] In one embodiment, a correction weight corresponding to a predetermined remaining capacity range may be set based on the ratio of the slope of the prediction line (501) corresponding to the predetermined remaining capacity range and the target line (502) corresponding to the predetermined remaining capacity range. For example, the correction weight corresponding to the predetermined remaining capacity range may be set as a value obtained by dividing the slope of the prediction line (501) corresponding to the predetermined remaining capacity range by the slope of the target line (502) corresponding to the predetermined remaining capacity range.

[0076] In one embodiment, the correction weights set corresponding to the vehicle (120) may include a first weight corresponding to the first section (510), a second weight corresponding to the second section (520), and a third weight corresponding to the third section (530). At this time, the first weight may be set as a value obtained by dividing the slope of the prediction line (501) corresponding to the first section (510) by the slope of the target line (502), the second weight may be set as a value obtained by dividing the slope of the prediction line (501) corresponding to the second section (520) by the slope of the target line (502), and the third weight may be set as a value obtained by dividing the slope of the prediction line (501) corresponding to the third section (530) by the slope of the target line (502).

[0077] In one embodiment, the correction weight may be set based on the state information of the vehicle (120). The state information according to one embodiment may include charge / discharge history data such as the charge / discharge cycle of the battery pack, environmental data such as the history of external temperature changes of the vehicle (120), and driving history data such as driving and idle status. For example, the state information may include the total driving distance as driving history data of the vehicle (120).

[0078] In one embodiment, the estimation device (110) can determine a prediction line (501) based on state information of the vehicle (120). Subsequently, the estimation device (110) can set a correction weight based on the determined prediction line (501) and generate an estimated remaining capacity of the battery pack mounted on the vehicle (120) based on time series data of the battery pack mounted on the vehicle (120) and the set correction weight.

[0079] Figure 6 is a graph showing the current measurement values ​​of the battery pack.

[0080] The graph shown in Fig. 6 illustrates the relationship between the remaining capacity estimated according to the prior art and the current value calculated through the measurement. In this case, the horizontal axis represents the remaining capacity, and the vertical axis represents the current value.

[0081] Referring to FIG. 6, the first line (610) represents a residual capacity-current value relationship corresponding to a vehicle with a driving distance of approximately 2000 km, and the second line (620) represents a residual capacity-current value relationship corresponding to a vehicle with a driving distance of approximately 12000 km.

[0082] In one embodiment, the estimation device (110) can calculate the change in remaining capacity per time interval by applying a correction weight to the current integration value of the current data for at least one time interval. At this time, the current integration value is the total amount of current flowing over time and may represent the amount of charge charged or discharged to the battery for a predetermined period.

[0083] Meanwhile, the specific process of calculating the change in remaining capacity per time interval by applying a correction weight to the current integration value of the current data for at least one time interval will be described later with reference to Fig. 7.

[0084] In one embodiment, the estimation device (110) can calculate the estimated remaining capacity for the first time point by accumulating the amount of change in remaining capacity for each time interval between the second time point and the first time point into the second estimated remaining capacity corresponding to the second time point.

[0085] In one embodiment, the first point in time represents a current point in time that changes in real time, and the second point in time may represent a fixed point in time. For example, the second point in time may represent a point in time when driving begins with the battery pack mounted on the vehicle fully charged, or a point in time when charging begins with the battery pack mounted on the vehicle fully discharged.

[0086] In one embodiment, the battery pack may not be fully charged or fully discharged between the second time point and the first time point. According to one embodiment, by estimating the remaining capacity using a correction weight, the remaining capacity at the first time point, which is outside the fully charged or fully discharged state where the remaining capacity of the battery can be verified relatively accurately, can be estimated with high accuracy.

[0087] Meanwhile, as time progresses, the interval between the first point in time representing the current time and the second point in time representing a fixed time may increase. In one embodiment, the estimation device (110) may detect atypical patterns (630) appearing in the time series data. For example, atypical patterns (630) may include the occurrence of discontinuous intervals in current data.

[0088] Subsequently, the estimation device (110) can change the atypical pattern (630) appearing in the time series data into replacement data. The atypical pattern (630) may be considered as an error in measurement caused by sudden changes in the environment or degradation of sensor performance, and the estimation device (110) can change the atypical pattern (630) into predicted replacement data using time series data surrounding the atypical pattern (630). At this time, the replacement data may include the average of data or moving average of adjacent time intervals. By changing the atypical pattern (630) appearing in the time series data into replacement data, the accuracy of the remaining capacity estimation can be improved.

[0089] In one embodiment, between the second time point and the first time point, the battery pack may be discharged as the vehicle (120) drives and charged as the vehicle (120) regeneratively brakes. At this time, regenerative braking is a process of recovering energy generated when the vehicle (120) performs braking and recharging the battery pack. As the charging and discharging cycle is shortened due to regenerative braking, the error in estimating the remaining capacity according to the prior art may increase. According to one embodiment, by estimating the remaining capacity using a correction weight, the remaining capacity at the first time point can be estimated with high accuracy despite frequent charging and discharging due to regenerative braking.

[0090] FIG. 7 is an exemplary drawing for explaining the process of calculating a predetermined remaining capacity change amount for a predetermined time interval. Meanwhile, the first interval (711), the second interval (712), and the third interval (713) shown in FIG. 7 may correspond to the first interval (510), the second interval (520), or the third interval (530) shown in FIG. 5, respectively.

[0091] Referring to FIG. 7, the estimation device (710) can estimate the remaining capacity of the vehicle (120) as shown in the estimation line (701). Meanwhile, FIG. 7 is illustrated as having a linear relationship with time for convenience of explanation, but the actual estimated remaining capacity of the vehicle (120) may not have a linear relationship with time.

[0092] In one embodiment, the estimation device (110) divides the time between a second time point and a first time point into a plurality of time intervals, and for each of the plurality of time intervals, calculates a predetermined remaining capacity change amount for a predetermined time interval by applying a weight corresponding to a predetermined time interval among a plurality of weights to a current integration value corresponding to a predetermined time interval. Meanwhile, the plurality of time intervals may be divided to have a preset time interval, but are not limited thereto.

[0093] In one embodiment, the estimation device (110) may include a predetermined remaining capacity change amount for a predetermined time interval by performing a multiplication operation on a current integration value corresponding to a predetermined time interval with a weight corresponding to a predetermined time interval.

[0094] For example, a predetermined time interval may correspond to a predetermined remaining capacity interval through the remaining capacity predicted in that time interval. Additionally, the predetermined time interval may correspond to a correction weight set in a predetermined remaining capacity interval through the predetermined remaining capacity interval.

[0095] As a specific example, the time interval (720) illustrated in FIG. 7 may correspond to the first interval (711) based on the remaining capacity estimated at that time. If a first weight, a second weight, or a third weight is set for each of the first interval (711), the second interval (712), and the third interval (713), the weight corresponding to the time interval (720) may represent the first weight set for the first interval (711). The estimation device (110) can calculate the change in remaining capacity for the time interval (720) by applying the first weight to the current integration value of the time interval (720).

[0096] The estimation device (110) can calculate the change in remaining capacity for each time interval by applying a weight corresponding to each time interval among the first weight, the second weight, and the third weight to the current integration value corresponding to each of all time intervals between the first time point and the second time point, just like the time interval (720). Subsequently, the estimation device (110) can generate the estimated remaining capacity for the first time point by accumulating the calculated change in remaining capacity for each time interval into the remaining capacity of the second time point.

[0097] In one embodiment, each change in remaining capacity for each time interval may have a positive or negative value. For example, when the vehicle (120) is discharging, such as while driving, the change in remaining capacity may have a negative value, and when the vehicle (120) is charging, such as through regenerative braking, the change in remaining capacity may have a positive value.

[0098] In one embodiment, the correction weight includes at least one charge correction weight and at least one discharge correction weight, and a plurality of time intervals may each correspond to charging or discharging.

[0099] The characteristics of the time series data-remaining capacity relationship appearing in the 0-100% charging test and the characteristics of the time series data-remaining capacity relationship appearing in the 100-0% discharging test may differ. The prediction line (501) shown in FIG. 5 may represent a prediction line predicted during charging or a prediction line predicted during discharging, and the charging correction weight may be set based on the prediction line predicted during charging, and the discharging correction weight may be set based on the prediction line predicted during discharging.

[0100] In one embodiment, the estimation device (110) can calculate a predetermined remaining capacity change amount by applying a charging correction weight to a current integration value corresponding to a predetermined time interval when the predetermined time interval between a first time point and a second time point corresponds to charging, and by applying a discharge correction weight to a current integration value corresponding to a predetermined time interval when the predetermined time interval corresponds to discharging. Subsequently, the estimation device (110) can generate an estimated remaining capacity at the first time point by accumulating the calculated remaining capacity change amount for each time interval into the remaining capacity at the second time point.

[0101] Figure 8 is an exemplary diagram illustrating the process of generating correction weights based on state information using a previously trained prediction model.

[0102] Referring to FIG. 8, the estimation device (110) can generate a correction weight (802) based on state information (801) using a previously learned prediction model (810), and calculate an estimated remaining capacity based on the acquired time series data and the generated correction weight (802). At this time, the prediction model (810) can generate a correction weight (802) corresponding to the vehicle (120) as an output using state information (801) for the vehicle (120) as an input.

[0103] The prediction model (810) may include at least one previously trained learning model. In this case, the learning model according to one embodiment may include a learning model based on at least one of various artificial neural network architectures such as MLP (Multilayer Perceptron), DNN (Deep Neural Network), CNN (Convolutional Neural Network), RNN (Recurrent Neural Network), LSTM (Long Short-Term Memory), GRU (Gated Recurrent Unit), Transformer, or Autoencoder.

[0104] In addition, a learning model according to one embodiment may include a learning model based on at least one of various machine learning algorithms, such as Random Forest, Support Vector Machine (SVM), or XGBoost (Extreme Gradient Boosting). In addition, a learning model according to one embodiment may include a learning model based on at least one of various data analysis techniques, such as Principal Component Analysis (PCA) or Independent Component Analysis (ICA).

[0105] In one embodiment, the prediction model (810) may include a learning model learned based on learning data (820). In this case, the learning data (820) may be configured using information regarding battery packs corresponding to each of the plurality of vehicles (130) described above with reference to FIG. 1. The learning data according to one embodiment may include charging test results and discharging test results corresponding to each of the plurality of vehicles (130).

[0106] Meanwhile, the charging test results and discharging test results corresponding to each of the multiple vehicles (130) may include test results based on the remaining capacity predicted through an algorithm according to the prior art, such that the minimum remaining capacity does not show 0% or the maximum remaining capacity does not show 100%. In order to configure the learning data (820) for effective learning, preprocessing of the charging test results and discharging test results may be performed during the process of configuring the learning data (820).

[0107] For example, in the case of test results where the minimum remaining capacity does not show 0% or the maximum remaining capacity does not show 100%, the test results may be adjusted according to the ratio so that the minimum remaining capacity shows 0% and the maximum remaining capacity shows 100%. Through this, only the relationship between the time series data and the remaining capacity derived from the algorithm according to the prior art can be appropriately utilized.

[0108] In addition, the learning data according to one embodiment may include state information such as charge / discharge history data, such as the charge / discharge cycle of a battery pack corresponding to each of a plurality of vehicles (130), environmental data, such as the history of external temperature changes of the vehicle (130), and driving history data, such as driving and idle status.

[0109] Through this, a prediction model (810) according to one embodiment can be used to output a correction weight (802) applicable to the vehicle (120) with high accuracy by using the state information (801) of the vehicle (120) as input.

[0110] Meanwhile, in another embodiment, the prediction model (810) may include a learning model that outputs a prediction line (501) instead of directly outputting a correction weight (802). The estimation device (110) can use the prediction model (810) to generate a prediction line (501) that reflects a trend appearing in other vehicles (130) having similar state information to the vehicle (120), based on the state information (801) of the vehicle (120). Subsequently, the estimation device (110) can generate a correction weight (802) corresponding to the vehicle (120) based on the predicted prediction line (501).

[0111] Through this, a prediction model (810) according to one embodiment can be used to generate a prediction line (501) for a vehicle (120) using state information (801) of the vehicle (120) as input, and an estimation device (110) can generate a correction weight (802) applicable to the vehicle (120) with high accuracy using the generated prediction line (501).

[0112] FIG. 9 is a block diagram of an estimation device according to one embodiment. The estimation device (900) shown in FIG. 9 may correspond to the estimation device (110) shown in FIG. 1.

[0113] Referring to FIG. 9, the estimation device (900) may include a processor (910), memory (920), and a communication module (930). Only the components related to the embodiment are shown in the estimation device (900) of FIG. 9. Therefore, a person skilled in the art will understand that other general-purpose components may be included in addition to the components shown in FIG. 9.

[0114] The processor (910) controls the overall operation of the estimation device (900). For example, the processor (910) can control the memory (920), communication module (930), input unit (not shown) and / or output unit (not shown), etc., by executing programs stored in the memory (920). The processor (910) can control the operation of the estimation device (900) by executing programs stored in the memory (920).

[0115] The processor (910) can control at least some of the operations of the estimation device (900) described above with reference to FIGS. 1 to 8. For example, the processor (910) can control a communication module to acquire time-series data for a battery pack mounted on a vehicle and supplying power to the motor of the vehicle, and can calculate a first estimated remaining capacity of the battery pack for a first time point based on the time-series data and a correction weight.

[0116] Meanwhile, a specific example of the operation of the processor (910) is the same as described above with reference to FIGS. 1 to 8. Therefore, a specific description of the operation of the processor (910) is omitted below.

[0117] The processor (910) may be implemented using at least one of ASICs (Application Specific Integrated Circuits), DSPs (Digital Signal Processors), DSPDs (Digital Signal Processing Devices), PLDs (Programmable Logic Devices), FPGAs (Field Programmable Gate Arrays), controllers, microcontrollers, microprocessors, and other electrical units for performing functions.

[0118] The memory (920) is hardware that stores various data processed within the estimation device (900) and can store programs for various operations, processing, and control of the processor (910).

[0119] The memory (920) may include RAM (Random Access Memory), such as DRAM (Dynamic Random Access Memory) and SRAM (Static Random Access Memory), ROM (Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), CD-ROM, Blu-ray or other optical disc storage, HDD (hard disk drive), SSD (solid state drive), or flash memory.

[0120] The communication module (930) may include at least one component that enables the estimation device (900) to perform wired / wireless communication with another device. For example, the communication module (930) may include a short-range communication unit and / or a mobile communication unit, but is not limited thereto.

[0121] Meanwhile, embodiments according to the present disclosure may be implemented in the form of a computer program that can be executed through various components on a computer, and such a computer program may be recorded on a computer-readable medium. In this case, the medium may include, but is not limited to, magnetic media such as hard disks, floppy disks, and magnetic tapes, optical recording media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, and hardware devices specifically configured to store and execute program instructions such as ROM, RAM, and flash memory.

[0122] Meanwhile, the above computer program may be one specifically designed and configured for the present disclosure or one known and available to those skilled in the art of computer software. Examples of computer programs may include machine code, such as that produced by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc.

[0123] According to one embodiment, the method according to various embodiments of the present disclosure may be provided by being included in a computer program product. The computer program product may be traded between a seller and a buyer as a product. The computer program product may be distributed in the form of a device-readable storage medium (e.g., compact disc read-only memory (CD-ROM)), or distributed online (e.g., download or upload) through an application store (e.g., Play Store™) or directly between two user devices. In the case of online distribution, at least a portion of the computer program product may be temporarily stored or temporarily created in a device-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or a relay server.

[0124] Unless explicitly stated otherwise, the steps constituting the method according to the present disclosure may be performed in a suitable order. The present disclosure is not necessarily limited by the order in which the steps are described. The use of any examples or exemplary terms (e.g., etc.) in the present disclosure is merely for the purpose of describing the present disclosure in detail and, unless limited by the claims, the scope of the present disclosure is not limited by such examples or exemplary terms. Furthermore, those skilled in the art will understand that various modifications, combinations, and changes may be made according to design conditions and factors within the scope of the claims or equivalents to which they are added.

[0125] Accordingly, the scope of the present disclosure should not be limited to the embodiments described above, and all scopes equivalent to or equivalently modified from the claims set forth below, as well as the claims set forth below, shall be considered to fall within the scope of the scope of the present disclosure.

Claims

Claim 1 A method for estimating the capacity of a battery mounted on a vehicle, comprising: a step of acquiring time series data for a battery pack mounted on a vehicle and supplying power to a motor of the vehicle; and a step of calculating a first estimated remaining capacity of the battery pack at a first time point based on the time series data and a correction weight; wherein the correction weight is set based on state information including the total driving distance of the vehicle. Claim 2 A method according to claim 1, wherein the time series data includes current data of the battery pack, and the calculating step comprises: a step of calculating the change in remaining capacity per time interval by applying the correction weight to the current integrated value of the current data for at least one time interval; and a step of calculating the first estimated remaining capacity by accumulating the change in remaining capacity per time interval between the second time point and the first time point to the second estimated remaining capacity corresponding to the second time point. Claim 3 In claim 2, the correction weighting comprises a plurality of weightings set for each remaining capacity interval. Claim 4 In claim 3, the step of calculating the change in remaining capacity for each time interval comprises: a step of dividing the time between the second time point and the first time point into a plurality of time intervals; and a step of calculating a predetermined change in remaining capacity for a predetermined time interval by applying a weight corresponding to the predetermined time interval among the plurality of weights to a current integration value corresponding to a predetermined time interval for each of the plurality of time intervals. Claim 5 In claim 4, the correction weight comprises at least one charge correction weight and at least one discharge correction weight, wherein the plurality of time intervals each correspond to charging or discharging, and the step of calculating the predetermined remaining capacity change amount comprises: applying the charge correction weight to a current integration value corresponding to the predetermined time interval when the predetermined time interval corresponds to charging, and applying the discharge correction weight to a current integration value corresponding to the predetermined time interval when the predetermined time interval corresponds to discharging; the method. Claim 6 In claim 2, a method in which the battery pack is not fully charged or fully discharged between the second time point and the first time point. Claim 7 A method according to claim 2, wherein between the second time point and the first time point, the battery pack is discharged according to the driving of the vehicle and charged according to the regenerative braking of the vehicle. Claim 8 A method according to claim 1, wherein the calculating step comprises: a step of generating the correction weight based on the state information using a previously learned prediction model; and a step of calculating the first estimated remaining capacity based on the time series data and the generated correction weight. Claim 9 A device for estimating the capacity of a battery mounted on a vehicle, comprising: a communication module; a memory in which at least one program is stored; and a processor that operates by executing the at least one program, wherein the processor controls the communication module to acquire time-series data for a battery pack mounted on a vehicle and supplying power to a motor of the vehicle, and calculates a first estimated remaining capacity of the battery pack at a first time point based on the time-series data and a correction weight, wherein the correction weight is set based on state information including the total driving distance of the vehicle. Claim 10 An apparatus according to claim 9, wherein the time series data includes current data of the battery pack, and the calculation comprises calculating the change in remaining capacity per time interval by applying the correction weight to the current integrated value of the current data for at least one time interval, and calculating the first estimated remaining capacity by accumulating the change in remaining capacity per time interval between the second time point and the first time point to the second estimated remaining capacity corresponding to the second time point. Claim 11 In claim 10, the device wherein the correction weighting comprises a plurality of weightings set for each remaining capacity interval. Claim 12 In claim 11, the apparatus for calculating the change in remaining capacity for each time interval comprises dividing the time between the second time point and the first time point into a plurality of time intervals, and for each of the plurality of time intervals, calculating a predetermined change in remaining capacity for the predetermined time interval by applying a weight corresponding to the predetermined time interval among the plurality of weights to a current integration value corresponding to the predetermined time interval. Claim 13 In claim 12, the correction weight comprises at least one charge correction weight and at least one discharge correction weight, wherein the plurality of time intervals each correspond to charging or discharging, and calculating the predetermined remaining capacity change amount comprises applying the charge correction weight to a current integration value corresponding to the predetermined time interval when the predetermined time interval corresponds to charging, and applying the discharge correction weight to a current integration value corresponding to the predetermined time interval when the predetermined time interval corresponds to discharging. Claim 14 In claim 10, the device wherein the battery pack is not fully charged or fully discharged between the second point in time and the first point in time. Claim 15 A device according to claim 10, wherein between the second time point and the first time point, the battery pack is discharged according to the driving of the vehicle and charged according to the regenerative braking of the vehicle. Claim 16 An apparatus according to claim 9, wherein the calculation comprises generating the correction weights based on the state information using a previously learned prediction model, and calculating the first estimated remaining capacity based on the time series data and the generated correction weights. Claim 17 A computer-readable, non-transient recording medium storing a program for executing the method according to claim 1 on a computer.

Images