Operation-linked predictive maintenance apparatus based on battery state data of shared electric mobility

Abstract

The present invention relates to an operation-linked predictive maintenance device based on battery status data of shared electric mobility, wherein the device comprises: a battery operation profile processing unit that performs authentication for a user account and manages a battery operation profile including battery maintenance history of a shared electric mobility vehicle linked to the user account; a battery status profile processing unit that manages a battery status profile including a charge status, discharge pattern, and degradation indicator of the battery based on battery status data collected from the shared electric mobility vehicle; a predictive maintenance analysis unit that inputs the battery operation profile and the battery status profile into a predictive maintenance model to predict the remaining lifespan or failure time of the battery; and an operation-linked sharing unit that predicts the time when maintenance is required for the shared electric mobility vehicle based on the remaining lifespan or failure time of the battery, and sets vehicle usage restrictions at the time when maintenance is required to determine whether to inspect and replace the battery, thereby sharing vehicle predictive maintenance operations linked to the user account.

Description

Technology Field

[0001] The present invention relates to maintenance technology for shared electric mobility, and more specifically, to an operation-linked predictive maintenance device based on battery status data of shared electric mobility that performs predictive maintenance based on a battery operation profile and battery status data and links the results with vehicle operation. Background Technology

[0003] Due to the nature of shared electric mobility services, where a single vehicle is operated continuously by multiple users, battery charging cycles, discharge patterns, and usage loads are inconsistent and vary significantly depending on driving habits. For example, users who accelerate or decelerate excessively place concentrated instantaneous loads on the battery, while users who repeatedly drive for long periods increase the cumulative discharge rate, which can accelerate the rate of battery degradation. These characteristics make it difficult to calculate battery degradation indicators in a consistent manner and cause problems where battery remaining life prediction models fail to reflect variability among users.

[0004] Furthermore, since shared electric mobility vehicles have a higher operating turnover rate and shorter charging and discharging cycles compared to general personal electric mobility, battery condition management is directly linked to the stability of service operations. However, conventional technologies have primarily relied on methods to assess battery aging based on single indicators such as charge status or accumulated mileage, failing to adequately consider that actual battery degradation is complexly influenced by factors that vary dynamically over the time axis, such as the rate of change in discharge power, current load, and temperature fluctuations.

[0005] There are also several limitations in terms of predictive maintenance technology. Conventional predictive maintenance systems calculate remaining lifespan or failure timing based on battery degradation models; however, they often treat parameters of different natures, such as degradation weights and degradation rate coefficients, as the same input dimension, failing to accurately reflect actual degradation trends. Furthermore, even if degradation trends are extrapolated along the time axis, prediction errors increase unless the results are continuously corrected by comparing them with actual measured battery status data. Consequently, this leads to a problem where the reliability of determining the maintenance timing is reduced.

[0006] Meanwhile, the fact that predicted failure times or remaining lifespans cannot be directly utilized in vehicle operations is also a significant issue in the shared electric mobility sector. Since shared electric mobility operates in a manner open to a large number of users rather than specific ones, the continued dispatch of vehicles due for maintenance can lead to a decline in service quality or a risk of breakdowns during operation. Nevertheless, conventional technologies have lacked the ability to organically integrate predictive maintenance results with operational systems—such as vehicle usage restrictions, user notifications, or station placement—making it difficult to reflect the effectiveness of predictive maintenance in actual service operations.

[0007] Accordingly, the present invention aims to provide a technology for predicting the timing of maintenance requirements and setting usage restrictions for electric mobility, wherein the matching or allocation logic for delivery orders is not included within the scope of the present invention.

[0008] Korean Published Patent No. 10-2014-0146411 relates to a vehicle status information sharing device and comprises: a data collection unit that collects vehicle status information data in a first communication data format; a data conversion unit that converts the status information data in the first communication data format collected by the data collection unit into a second communication data format; and a wireless communication unit that transmits the status information data in the second communication data format converted by the data conversion unit to a pre-configured cloud service server. Prior art literature

[0010] Korean Published Patent No. 10-2014-0146411 (December 26, 2014) The problem to be solved

[0011] One embodiment of the present invention aims to provide an operation-linked predictive maintenance device based on battery status data of shared electric mobility that can precisely manage a battery operation profile by processing user account-based battery maintenance history and driving habit information into a consistent data structure.

[0012] One embodiment of the present invention aims to provide an operation-linked predictive maintenance device based on battery status data of shared electric mobility, which can accurately calculate the degree of battery degradation by analyzing battery status data, including charge state, discharge pattern, and degradation indicator, on a time axis.

[0013] One embodiment of the present invention aims to provide an operation-linked predictive maintenance device based on battery status data of shared electric mobility, which predicts the remaining lifespan or the time of failure using a predictive maintenance model and automatically applies the maintenance timing during the actual service operation phase by linking the prediction results with vehicle usage restrictions or user guidance. means of solving the problem

[0015] Among the embodiments, an operation-linked predictive maintenance device based on battery status data of a shared electric mobility vehicle comprises: a battery operation profile processing unit that performs authentication for a user account and manages a battery operation profile including the battery maintenance history of a shared electric mobility vehicle linked to the user account; a battery status profile processing unit that manages a battery status profile including the charge status, discharge pattern, and degradation indicator of the battery based on battery status data collected from the shared electric mobility vehicle; a predictive maintenance analysis unit that inputs the battery operation profile and the battery status profile into a predictive maintenance model to predict the remaining lifespan or failure time of the battery; and an operation-linked sharing unit that predicts the time when maintenance is required for the shared electric mobility vehicle based on the remaining lifespan or failure time of the battery, and sets vehicle usage restrictions at the time when maintenance is required to determine whether to inspect and replace the battery, thereby sharing the vehicle predictive maintenance operation linked to the user account.

[0016] The battery operation profile processing unit can determine the user's driving habits, including acceleration frequency, deceleration pattern, or driving duration, through linkage with the user account, and calculate the battery degradation weight of the predictive maintenance model by reflecting the driving habits in the battery maintenance history.

[0017] The battery state profile processing unit can calculate the discharge pattern based on the rate of change of discharge power relative to discharge time based on the charge state, and calculate the battery degradation rate coefficient of the predictive maintenance model by reflecting the discharge pattern in the degradation index.

[0018] The above predictive maintenance analysis unit can improve the prediction accuracy of the remaining lifespan of the battery by using a multi-parameter predictive maintenance model that processes the battery degradation weight and battery degradation rate coefficient of the above predictive maintenance model by separating them into different input dimensions.

[0019] The above predictive maintenance analysis unit can predict the time of failure of the battery by extrapolating the battery degradation trend on the time axis using the battery degradation rate coefficient and correcting the extrapolated degradation trend according to the user's driving habits using the battery degradation weight.

[0020] The above-mentioned operation linkage sharing unit can share the vehicle predictive maintenance operation by notifying the user of the above-mentioned user account of the remaining usage time due to the vehicle usage restriction based on the above-mentioned maintenance required time, and when the above-mentioned maintenance required time has elapsed, providing priority guidance on the location information of a mobility station selectable by the user during the movement of the above-mentioned shared electric mobility vehicle.

[0021] The above status data may include not only the battery status data but also abnormal current, vibration, thermal status, and fault code information of the motor, inverter, reduction gear, and drive system control unit. Effects of the invention

[0023] The disclosed technology may have the following effects. However, this does not mean that a specific embodiment must include all of the following effects or only the following effects; therefore, the scope of the rights of the disclosed technology should not be understood as being limited by this.

[0024] An operation-linked predictive maintenance device based on battery status data of shared electric mobility according to one embodiment of the present invention can precisely manage a battery operation profile by processing user account-based battery maintenance history and driving habit information into a consistent data structure.

[0025] An operation-linked predictive maintenance device based on battery status data of shared electric mobility according to one embodiment of the present invention can accurately calculate the degree of battery degradation by analyzing battery status data, including charging status, discharge pattern, and degradation indicator, based on a time axis.

[0026] An operation-linked predictive maintenance device based on battery status data of shared electric mobility according to one embodiment of the present invention can predict the remaining lifespan or the time of failure using a predictive maintenance model, and automatically apply the maintenance time during the actual service operation phase by linking the prediction result with vehicle usage restrictions or user guidance. Brief explanation of the drawing

[0028] FIG. 1 is a drawing illustrating an operation-linked predictive maintenance system according to one embodiment of the present invention. Figure 2 is a diagram illustrating the system configuration of the operation-linked predictive maintenance device of Figure 1. Figure 3 is a diagram illustrating the functional configuration of the operation-linked predictive maintenance device of Figure 1. FIG. 4 is a flowchart illustrating the functional configuration of an operation-linked predictive maintenance device according to the present invention. FIG. 5 is a diagram illustrating an information linkage structure between a user terminal and a shared electric mobility vehicle according to an embodiment of an operation-linked predictive maintenance device. Specific details for implementing the invention

[0029] The description of the present invention is merely an example for structural or functional explanation, and therefore the scope of the present invention should not be interpreted as being limited by the examples described in the text. That is, since the examples are subject to various modifications and may take various forms, the scope of the present invention should be understood to include equivalents capable of realizing the technical concept. Furthermore, the objectives or effects presented in the present invention do not imply that a specific example must include all of them or only such effects; therefore, the scope of the present invention should not be understood as being limited by them.

[0030] Meanwhile, the meaning of the terms described in this application should be understood as follows.

[0031] Terms such as "first," "second," etc., are intended to distinguish one component from another, and the scope of rights shall not be limited by these terms. For example, the first component may be named the second component, and similarly, the second component may be named the first component.

[0032] When it is stated that one component is "connected" to another component, it should be understood that it may be directly connected to that other component, or that there may be other components in between. Conversely, when it is stated that one component is "directly connected" to another component, it should be understood that there are no other components in between. Meanwhile, other expressions describing the relationships between components, such as "between" and "exactly between," or "adjacent to" and "directly adjacent to," should be interpreted in the same way.

[0033] A singular expression should be understood to include a plural expression unless the context clearly indicates otherwise, and terms such as "include" or "have" are intended to specify the existence of the implemented features, numbers, steps, actions, components, parts, or combinations thereof, and should be understood not to preclude the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.

[0034] In each step, identifiers (e.g., a, b, c, etc.) are used for convenience of explanation and do not describe the order of the steps; the steps may occur differently from the specified order unless a specific order is clearly indicated in the context. That is, the steps may occur in the same order as specified, may be performed substantially simultaneously, or may be performed in the reverse order.

[0035] The present invention may be implemented as computer-readable code on a computer-readable recording medium, and the computer-readable recording medium includes all types of recording devices in which data that can be read by a computer system is stored. Examples of computer-readable recording media include ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage device, etc. Additionally, the computer-readable recording medium may be distributed across networked computer systems, so that computer-readable code can be stored and executed in a distributed manner.

[0036] Unless otherwise defined, all terms used herein have the same meaning as generally understood by those skilled in the art to which this invention pertains. Terms defined in commonly used dictionaries should be interpreted as having meanings consistent with the context of the relevant technology and should not be interpreted as having an ideal or overly formal meaning unless explicitly defined in this application.

[0038] FIG. 1 is a drawing illustrating an operation-linked predictive maintenance system according to one embodiment of the present invention.

[0039] Referring to FIG. 1, the operation-linked predictive maintenance system (100) may include a user terminal (110), a shared electric mobility vehicle (120), an operation-linked predictive maintenance device (130), and a database (150).

[0040] The user terminal (110) may correspond to a computing device capable of providing execution results and related information of the operation-linked predictive maintenance device (130). To this end, the user terminal (110) may install a dedicated application or software to receive and process data regarding battery operation profiles, battery status profiles, and predictive maintenance analysis results in real time through a dedicated application or software linked to the operation-linked predictive maintenance system (100). Here, the dedicated application may provide the user with the remaining battery life, failure time, maintenance time, and vehicle usage restriction information in the form of a visualization and dashboard during the operation-linked predictive maintenance process based on battery status data of shared electric mobility, thereby providing the user with the predictive maintenance progress status and maintenance linkage results of the operation-linked predictive maintenance system (100).

[0041] The user terminal (110) may be composed of a single or multiple units, and if composed of multiple units, it may include a first user terminal, a second user terminal, ..., the nth (n is a natural number) user terminal. For example, the user terminal (110) may be implemented as a smartphone, laptop, or computer capable of operating in connection with the operation-linked predictive maintenance device (130), but is not necessarily limited thereto and may be implemented as various devices including a tablet PC. In addition, the user terminal (110) may be connected to the operation-linked predictive maintenance device (130) via a network, but is not necessarily limited thereto, and multiple user terminals (110) may be connected to the operation-linked predictive maintenance device (130) simultaneously.

[0042] A shared electric mobility vehicle (120) may correspond to a mobile mobility device that provides battery status data. For example, the shared electric mobility vehicle (120) may include a battery pack, a drive motor, a driving control module, and a battery data collection sensor, but is not limited thereto. It may be connected via a network with an operation-linked predictive maintenance device (130) to provide data related to the battery's charge status, discharge pattern, and degradation indicators in real time. Additionally, the shared electric mobility vehicle (120) may be subject to usage restriction control regarding the timing of maintenance required by the operation-linked predictive maintenance device (130) based on the results of the predictive maintenance analysis.

[0043] The operation-linked predictive maintenance device (130) may be implemented as a server corresponding to a computer or program that performs an operation-linked predictive maintenance method based on battery status data of shared electric mobility according to the present invention. The operation-linked predictive maintenance device (130) may be implemented as a server that provides functions such as processing battery operation profiles, processing battery status profiles, predictive maintenance analysis, and setting vehicle usage restrictions, and each step of the operation-linked predictive maintenance method based on battery status data of shared electric mobility according to the present invention may be performed on the server.

[0044] Additionally, the operation-linked predictive maintenance device (130) is not necessarily limited to this and can be implemented as a server that calculates the time required for maintenance based on the remaining lifespan of the battery or the prediction result of the time of failure, and performs control linked to vehicle operation. The operation-linked predictive maintenance device (130) can be connected to the user terminal (110) via a wired network or a wireless network such as Bluetooth, WiFi, or LTE, and can transmit and receive data with the user terminal (110) through the wired or wireless network.

[0045] Additionally, the operation-linked predictive maintenance device (130) may be implemented to operate in connection with an independent external system (not shown in FIG. 1). For example, the operation-linked predictive maintenance device (130) may operate in conjunction with a shared electric mobility vehicle management system and a battery data collection system, and is not necessarily limited thereto, but may operate in conjunction with a maintenance management system and a user account authentication server. That is, the operation-linked predictive maintenance device (130) of the present invention may be implemented in a structure capable of being linked with various external systems to exchange battery operation profiles, battery status profiles, and predictive maintenance analysis results with external systems.

[0046] The database (150) may correspond to a storage device that stores various information required during the operation process of the operation-linked predictive maintenance device (130). For example, the database (150) may store various information such as battery operation profile data, battery status profile data, and predictive maintenance analysis result data. Additionally, the database (150) may support the stable execution of the predictive maintenance analysis process of the operation-linked predictive maintenance device (130) based on the stored information. The database (150) may store or update battery operation profile data and battery status profile data in conjunction with the operation-linked predictive maintenance device (130), and may also transmit the data to the user terminal (110) as needed. Furthermore, the database (150) may store data related to the calculation of the time required for maintenance in the operation-linked predictive maintenance process based on the battery status data of the shared electric mobility, and may support the setting of vehicle usage restrictions and user guidance processes based on the stored data related to the time required for maintenance.

[0047] In FIG. 1, the database (150) is shown as a device independent of the operation-linked predictive maintenance device (130), but it is not necessarily limited to this and can be implemented by being included in the operation-linked predictive maintenance device (130).

[0049] Figure 2 is a diagram illustrating the system configuration of an operation-linked predictive maintenance device based on battery status data of the shared electric mobility of Figure 1.

[0050] Referring to FIG. 2, the operation-linked predictive maintenance device (130) may include a processor (210), memory (230), user input / output unit (250), network input / output unit (270), and communication port unit (290).

[0051] The processor (210) can execute an operation-linked predictive maintenance procedure based on battery status data of a shared electric mobility according to an embodiment of the present invention, manage memory (230) that is read or written during this process, and schedule the synchronization time between volatile memory and non-volatile memory in memory (230). The processor (210) can control the overall operation of the operation-linked predictive maintenance device (130) and is electrically connected to memory (230), user input / output unit (250), and network input / output unit (270) to control the data flow between them. The processor (210) can be implemented as a CPU (Central Processing Unit) or GPU (Graphics Processing Unit) of the operation-linked predictive maintenance device (130).

[0052] The memory (230) may include an auxiliary storage device implemented as non-volatile memory such as an SSD (Solid State Disk) or HDD (Hard Disk Drive) and used to store all data required for the operation-linked predictive maintenance device (130), and may include a main memory device implemented as volatile memory such as RAM (Random Access Memory). Additionally, the memory (230) may store a set of instructions that execute an operation-linked predictive maintenance method based on battery status data of the shared electric mobility according to the present invention by being executed by an electrically connected processor (210).

[0053] The user input / output unit (250) includes an environment for receiving user input and an environment for outputting specific information to the user, and may include an input device including an adapter such as a touch pad, touch screen, virtual keyboard, or pointing device, and an output device including an adapter such as a monitor or touch screen. In one embodiment, the user input / output unit (250) may correspond to a computing device connected via remote access, and in such case, the operation-linked predictive maintenance device (130) may be performed as an independent server.

[0054] The network input / output unit (270) provides a communication environment for connecting to a user terminal (110) through a network and may include an adapter for communication such as a LAN (Local Area Network), MAN (Metropolitan Area Network), WAN (Wide Area Network), and VAN (Value Added Network). Additionally, the network input / output unit (270) may be implemented to provide short-range communication functions such as WiFi and Bluetooth, or wireless communication functions of 4G or higher, for wireless transmission of data.

[0055] The communication port section (290) can be implemented as a port mapping table that performs data routing during the process of transmitting and receiving data through a network. Here, the communication port section (290) can distinguish communication sessions between the user terminal (110) and the server and prevent data collisions during the process of transmitting and receiving data by assigning a unique source port to the user terminal (110).

[0057] Figure 3 is a diagram illustrating the functional configuration of an operation-linked predictive maintenance device based on battery status data of the shared electric mobility of Figure 1.

[0058] Referring to FIG. 3, the operation-linked predictive maintenance device (130) may include a battery operation profile processing unit (310), a battery status profile processing unit (330), a predictive maintenance analysis unit (350), an operation linkage sharing unit (370), and a control unit (390).

[0059] At this time, the embodiments of the present invention are not required to include all of the above functional configurations simultaneously; depending on each embodiment, some of the above configurations may be omitted, or some or all of the above configurations may be selectively included. Furthermore, one embodiment of the present invention may be implemented as an independent module that selectively includes some of the above configurations, and may perform an operation-linked predictive maintenance method based on battery status data of shared electric mobility through interoperability between the modules. The operation of each configuration will be described in detail below.

[0061] The battery operation profile processing unit (310) can perform authentication for a user account and manage a battery operation profile that includes the battery maintenance history of a shared electric mobility vehicle (120) linked to the user account. Here, the battery operation profile processing unit (310) can receive a login request from a user terminal (110) that includes identification information and authentication information of the user account to perform authentication for the user account, and can perform a procedure to verify whether it matches the stored user account information. For example, the battery operation profile processing unit (310) can determine whether the user account is a valid account registered to the shared electric mobility service by using various authentication means such as an ID and password, a one-time authentication code, and token-based authentication information.

[0062] Next, when authentication for the user account is successful, the battery operation profile processing unit (310) checks the linkage relationship between the user account and the shared electric mobility vehicle (120) and can query or create a battery operation profile including battery maintenance history for the shared electric mobility vehicle (120) linked to the user account. The battery operation profile processing unit (310) can track and manage changes in the maintenance history of the shared electric mobility vehicle (120) over time by storing maintenance history elements, such as battery replacement date, inspection date, maintenance type, maintenance details, information on parts used, and post-maintenance status evaluation results, included in the battery operation profile as structured data fields. Additionally, the battery operation profile processing unit (310) can maintain the latest state of the battery operation profile by updating the battery maintenance history through input from the maintenance system or operator whenever a new maintenance task is performed and reflecting the updated battery maintenance history. The battery operation profile processing unit (310) can store the battery operation profile in the database (150) and, if necessary, provide a function to view the battery maintenance history on a user account basis, a shared electric mobility vehicle (120) basis, or a period basis.

[0063] In one embodiment, the battery operation profile processing unit (310) can determine the user's driving habits, including acceleration frequency, deceleration pattern, or driving duration, through linkage with a user account, and calculate the battery degradation weight of the predictive maintenance model by reflecting the driving habits in the battery maintenance history. Here, the battery operation profile processing unit (310) can analyze the user's acceleration frequency, deceleration pattern, or driving duration by integrating driving data transmitted from the user terminal (110) and driving control data collected from the shared electric mobility vehicle (120) through linkage with a user account. Next, the battery operation profile processing unit (310) performs time synchronization of the driving data and driving control data and divides the data based on continuous driving sections to extract detailed driving indicators for each user account, including the rate of change of speed per time section, braking input strength, and continuous driving time, and can convert the user's driving habits into quantified driving characteristic parameters based on the extracted detailed driving indicators.

[0064] For example, the battery operation profile processing unit (310) can divide driving data based on the point in time when the amount of speed change exceeds or falls below a specific threshold to detect acceleration and deceleration events, and perform statistical processing to calculate the acceleration duration, deceleration intensity, and speed change pattern for each divided segment. Additionally, the battery operation profile processing unit (310) can calculate driving characteristic parameters that enhance the representativeness of driving habits by aligning detailed driving indicators to the same time axis and analyzing the correlation between the detailed driving indicators derived from the statistical processing results by comparing and analyzing the change trends of each indicator, thereby quantitatively reflecting driving habit elements such as the acceleration frequency, deceleration pattern, or driving duration of an individual driver.

[0065] In one embodiment, the battery operation profile processing unit (310) can reflect the determined driving habit in the battery operation profile along with the battery maintenance history, and can reconstruct the driving habit data value in the form of an input item required by the predictive maintenance model to evaluate the effect of the driving habit on battery degradation. Additionally, the battery operation profile processing unit (310) can calculate a battery degradation weight corresponding to the driving habit by considering the variability affecting the degree of battery aging when the driving habit is combined with the battery maintenance history, and transmit the calculated battery degradation weight to the predictive maintenance model so that the driving habit is reflected in the remaining life prediction process.

[0066] The battery state profile processing unit (330) can manage a battery state profile including the charge state, discharge pattern, and degradation indicator of the battery based on battery state data collected from the shared electric mobility vehicle (120). The battery state profile processing unit (330) can receive battery state-related data, including voltage, current, temperature, and charge state values, provided by a battery management device mounted on the shared electric mobility vehicle (120), in order to periodically collect battery state data from the shared electric mobility vehicle (120). The battery state profile processing unit (330) can store the received battery state data along with time information and manage it as part of the battery state profile by configuring a charge state history that indicates how the charge state of the battery changes over time for the same shared electric mobility vehicle (120).

[0067] Additionally, the battery state profile processing unit (330) can extract a section corresponding to the discharge section among the battery state data, analyze the current, power, and temperature change patterns in the discharge section to generate parameters representing the discharge pattern, and then manage the discharge pattern by including it in the battery state profile. Here, the battery state profile processing unit (330) can quantitatively express the progress of battery degradation by calculating battery degradation-related indicators such as changes in internal resistance, degree of capacity reduction, and degree of output degradation occurring during the repetitive charging and discharging process, defining the calculated values ​​as degradation indicators, and integrating them into the battery state profile. The battery state profile processing unit (330) can store the battery state profile in the database (150) on a unit basis for shared electric mobility vehicles (120), and manage it so that the charging state, discharge pattern, and degradation indicators of the battery corresponding to a specific vehicle, a specific period, or specific operating conditions can be queried as needed.

[0068] In one embodiment, the battery state profile processing unit (330) can calculate a discharge pattern based on the rate of change of discharge power relative to discharge time based on the charge state and calculate a battery degradation rate coefficient of the predictive maintenance model by reflecting the discharge pattern in the degradation index. The battery state profile processing unit (330) can collect battery state data to extract a charge state value indicating the charge state and an output power value over time, and calculate the change in discharge power corresponding to the discharge time for each charge state interval. The battery state profile processing unit (330) can calculate the rate of change of discharge power relative to discharge time using the time difference and the amount of fluctuation in power values ​​in the discharge interval, and define a discharge pattern by arranging this rate of change by charge state interval or expressing it as a statistical value such as the average, variance, and maximum value.

[0069] Additionally, the battery condition profile processing unit (330) can apply a mapping rule to increase the value of the degradation indicator when the rate of change of discharge power relative to discharge time exceeds a specific threshold range or increases in a constant trend in order to reflect the discharge pattern in the degradation indicator, and can manage the history of the degradation indicator so that the degradation indicator accumulates over time. The battery condition profile processing unit (330) can convert the degradation indicator reflected in this way into an input format required by the predictive maintenance model, and calculate the battery degradation rate coefficient of the predictive maintenance model by combining the fluctuation trend of the degradation indicator and the slope information of the discharge pattern.

[0070] In one embodiment, the battery state profile processing unit (330) can generate a multidimensional discharge pattern that reflects both the rate of change in power and the rate of change in temperature to define the discharge pattern. The battery state profile processing unit (330) can sort battery temperature data collected from a shared electric mobility vehicle (120) based on a time axis and simultaneously analyze the rate of change in discharge power and the rate of change in temperature on the same time axis. The battery state profile processing unit (330) calculates the slope of change of power and the rate of change in temperature in each time interval, and if the correlation between the slopes of the rate of change in power and the rate of change in temperature satisfies a specific threshold condition (e.g., the difference between the slopes of the rate of change in power and the rate of change in temperature is below a preset threshold, or the interval of simultaneous increase in the rates of change continues for a certain period of time or longer), it can identify this as a discharge characteristic interval and configure it as part of the multidimensional discharge pattern. For example, the battery state profile processing unit (330) can determine that the interval where the rate of change in power increases rapidly and the rate of change in temperature also increases is a interval where internal resistance increase or chemical degradation occurs in combination, and store it as an independent pattern element.

[0071] Next, the battery state profile processing unit (330) can calculate the degradation index by calculating the correlation values ​​of the power change-based pattern and the temperature change-based pattern to reflect the multidimensional discharge pattern in the degradation index, and increasing the weight of the degradation index for the section with a high correlation value. Additionally, the battery state profile processing unit (330) can track the degree to which each pattern element included in the multidimensional discharge pattern repeats over time, and adjust the cumulative value of the degradation index so that elements with a high frequency of repetition are reflected more significantly in the degradation index.

[0072] In one embodiment, the battery status profile processing unit (330) can improve the accuracy of determining the time when maintenance is needed by utilizing drivetrain status data included in the shared electric mobility vehicle (120) in addition to the battery status profile. Here, the drivetrain status data may include current, voltage, temperature, rotational speed, torque output, or efficiency degradation indicators generated by the motor, inverter, or controller. For example, the battery status profile processing unit (330) can determine whether the battery discharge rate increases abnormally in sections where the drivetrain load increases by comparing and analyzing the motor current change and battery discharge power change for each driving section based on the drivetrain status data on a time axis. Through this, the battery status profile processing unit (330) can distinguish whether battery degradation is caused by simple repeated charging and discharging or accelerated by an increase in drivetrain load, thereby determining the time when maintenance is needed more precisely.

[0073] Additionally, the battery condition profile processing unit (330) can manage abnormal current patterns detected in the motor or inverter among the drivetrain condition data, history of repeated overload occurrences, or frequency of fault code occurrences as auxiliary input elements of the degradation indicator to identify conditions in which battery degradation is accelerated by an increase in drivetrain load, and can process such that the rate of increase of the degradation indicator is amplified when such conditions occur repeatedly. The battery condition profile processing unit can analyze vibration signals or efficiency degradation trends included in the drivetrain condition data to quantify the impact of increased mechanical friction or control loss on the battery discharge pattern and provide the quantified impact as input data for a predictive maintenance model along with the degradation indicator included in the battery condition profile.

[0074] The predictive maintenance analysis unit (350) can predict the remaining lifespan of the battery or the time of failure by inputting the battery operation profile and the battery status profile into the predictive maintenance model. Here, the predictive maintenance model may correspond to a model that predicts the degradation trend by expressing the degradation characteristics of the battery as a mathematical model or a machine learning-based model, and, for example, may correspond to a time series prediction model that calculates the time of battery performance degradation by receiving the slope of the change in degradation indicators over time and the discharge pattern as input. The predictive maintenance analysis unit (350) can convert the battery operation profile and the battery status profile into an input format required by the predictive maintenance model and process the converted data by transmitting it to the predictive maintenance model to calculate the remaining lifespan of the battery or the time of failure. For example, the predictive maintenance analysis unit (350) can organize input data such that the battery maintenance history, driving habit information, and driving condition data included in the battery operation profile are aligned on a time axis basis, and the charge state, discharge pattern, and degradation indicators included in the battery state profile are combined on the same time axis basis so that the predictive maintenance model can comprehensively reflect the degradation progression characteristics of the battery.

[0075] Next, the predictive maintenance analysis unit (350) can provide elements such as the slope of change in the battery condition profile, the frequency of pattern repetition, and the accumulated amount of the degradation indicator in the form of continuous time series data so that the predictive maintenance model can analyze the cumulative trend of battery degradation, and can receive the remaining lifespan of the battery or the time of failure calculated by the predictive maintenance model and store it in the database (150). In addition, the predictive maintenance analysis unit (350) can verify whether the predicted remaining lifespan or predicted time of failure output by the predictive maintenance model satisfies specific stability criteria (e.g., conditions where the prediction error is within a pre-set allowable error range or the variability of the prediction result is maintained below a certain threshold), and can set it as a reference value for determining the time when maintenance is required based on the verification result.

[0076] In one embodiment, the predictive maintenance analysis unit (350) can improve the prediction accuracy of the remaining lifespan of a battery by using a multi-parameter predictive maintenance model that processes the battery degradation weight and battery degradation rate coefficient of the predictive maintenance model by separating them into different input dimensions. Here, the multi-parameter predictive maintenance model may correspond to a prediction model that interprets degradation progression characteristics in multiple dimensions by learning different battery degradation factors as independent input structures, and for example, may correspond to a time-series-based prediction model that calculates the remaining lifespan or the time of failure while minimizing mutual interference between input parameters by configuring the battery degradation weight and battery degradation rate coefficient as separate input axes. The predictive maintenance analysis unit (350) can process the battery degradation weight and battery degradation rate coefficient, which constitute the input of the predictive maintenance model, by not processing them as a single parameter in the same dimension, but by separating them into independent input dimensions and providing them to the multi-parameter predictive maintenance model, thereby allowing the degradation characteristics of the battery degradation weight and battery degradation rate coefficient parameters to be reflected individually.

[0077] Here, the predictive maintenance analysis unit (350) may arrange the battery degradation weight as an input dimension explaining the long-term degradation impact, considering that the battery degradation weight is a parameter representing the degree of battery burden according to driving habits, driving patterns, or maintenance history, and may configure it as a separate input dimension, considering that the battery degradation rate coefficient is a parameter representing the rate of degradation progression that changes in the short term according to discharge patterns or changes in charge state. The predictive maintenance analysis unit (350) can enable the predictive maintenance model to independently analyze degradation factors having different temporal characteristics through the separated input dimensions, and can adjust the model's learning structure so that the degradation weight and the degradation rate coefficient contribute to the prediction process without mutual interference. In addition, the predictive maintenance analysis unit (350) can distinguish and interpret whether the cause of battery performance degradation is a long-term or short-term factor through the results in which the separated input dimensions are individually reflected in the predictive maintenance model, and can calculate the remaining lifespan of the battery or the time of failure based on the interpretation results.

[0078] In one embodiment, the predictive maintenance analysis unit (350) can predict the time of failure of the battery by extrapolating the battery degradation trend on the time axis using the battery degradation rate coefficient and correcting the extrapolated degradation trend according to the user's driving habits using the battery degradation weight. The predictive maintenance analysis unit (350) can predict the time of failure of the battery by extrapolating the battery degradation trend on the time axis using the battery degradation rate coefficient and correcting the extrapolated degradation trend according to the user's driving habits using the battery degradation weight. First, the predictive maintenance analysis unit (350) can analyze the pattern of change in the degradation rate that appears during the process of the degradation index increasing over time by using the degradation progress rate by charge state interval, the slope of the discharge pattern change, and the cumulative change amount of the degradation index included in the battery degradation rate coefficient. The predictive maintenance analysis unit (350) can determine whether the deterioration index shows a linear increase, an accelerated increase, or a decelerated increase over time by calculating the hourly change amount of the deterioration index and calculating the first change rate and the second change rate of the calculated change amount.

[0079] In this analysis process, the predictive maintenance analysis unit (350) can quantitatively determine the rate of progression of degradation over time by calculating the first derivative and second derivative of the degradation index based on the amount of change of the value recorded in the previous time interval of the degradation index. If the rate of change of the degradation index exceeds a preset threshold slope value in a continuous time interval, the predictive maintenance analysis unit (350) determines that the degradation factor, such as an increase in internal resistance or a decrease in the electrode active area, is progressing rapidly, and can apply an extrapolation algorithm designed to increase the slope of the degradation trend curve by reflecting the result of this determination.

[0080] For example, the predictive maintenance analysis unit (350) can quantitatively reflect the degradation progress characteristics of the battery by applying a polynomial-based extrapolation technique, an exponential-based extrapolation technique, or a stochastic degradation model-based extrapolation technique to predict the degree of change of the degradation trend curve along the time axis, and automatically adjusting the coefficient value of the extrapolation technique according to the value of the degradation rate coefficient. Here, the predictive maintenance analysis unit (350) can determine the extrapolation technique by analyzing the hourly change amount of the degradation indicator, selecting a polynomial-based extrapolation technique when the degradation indicator maintains a constant growth rate in a certain section, and selecting an exponential-based extrapolation technique when the growth rate of the degradation indicator continuously increases after a specific point in time. The predictive maintenance analysis unit (350) can generate a trend of the degradation indicator increasing over time in the form of a continuous function using the selected extrapolation technique, and calculate the time to reach the degradation threshold by calculating the point in time when the generated degradation trend curve intersects with a value corresponding to the degradation threshold. Here, the predictive maintenance analysis unit (350) can determine the point in time when the deterioration trend curve crosses the deterioration threshold as the point in time when failure is possible and record the point in time as a prediction result.

[0081] Next, the predictive maintenance analysis unit (350) can apply battery degradation weights to the extrapolated degradation trend to consider the effect of user driving habits on the rate of battery degradation. The predictive maintenance analysis unit (350) can interpret the effects of acceleration frequency, deceleration pattern, and driving duration elements included in the battery degradation weights on battery degradation in the form of independent weighting coefficients, and reflect the corresponding weights in the slope of the extrapolated degradation curve, the slope of the change in the discharge pattern, or the cumulative amount of the degradation indicator to correct the rate of degradation under actual driving conditions. For example, in the case of a user with a high acceleration frequency and a rapid deceleration pattern, the degradation weight increases, so the predictive maintenance analysis unit (350) can correct that the time of failure is reached faster even with the same change in the degradation indicator in the extrapolated degradation trend. Conversely, the predictive maintenance analysis unit (350) can correct the degradation curve in a direction that reduces the degradation weighting and relatively delays the point at which the extrapolated degradation trend reaches the degradation threshold for users who have a constant driving duration and a gradual acceleration / deceleration pattern. Based on the corrected degradation trend, the predictive maintenance analysis unit (350) can calculate a confidence interval for the time of failure by integrating uncertainty factors such as the variability of the degradation trend, the dispersion of the degradation indicator, or the repetition frequency of the discharge pattern to account for the degradation deviation that may actually occur in the operating environment.

[0082] In one embodiment, the predictive maintenance analysis unit (350) can analyze the error between the extrapolation result of the degradation trend and the actual battery state data to update at least one of the battery degradation weight or the battery degradation rate coefficient, and re-predict the time of failure by reflecting the updated parameter. The predictive maintenance analysis unit (350) can analyze the error between the extrapolation result of the degradation trend and the actual battery state data to update at least one of the battery degradation weight or the battery degradation rate coefficient, and re-predict the time of failure by reflecting the updated parameter. Here, the predictive maintenance analysis unit (350) can calculate the predicted degradation index value for each time interval from the extrapolation result of the degradation trend, calculate the actual degradation index value using the battery state data in the same time interval, and then define the difference between the predicted degradation index value and the actual degradation index value as the error. The predictive maintenance analysis unit (350) can quantify the calculated error in the form of an absolute error, a squared error, or a mean squared error, and if the quantified error exceeds a preset allowable error range, it can determine that adjustment of the battery degradation weight or battery degradation rate coefficient is required.

[0083] Accordingly, the predictive maintenance analysis unit (350) can determine whether the battery degradation weight is overset or the battery degradation rate coefficient is underset based on the sign and magnitude of the error. The predictive maintenance analysis unit (350) can update the value by increasing or decreasing at least one of the battery degradation weight or the battery degradation rate coefficient according to the determined result. The predictive maintenance analysis unit (350) can update the battery degradation rate coefficient by increasing it when the predicted degradation index value consistently appears lower than the actual degradation index value, and update the battery degradation weight by decreasing it when the predicted degradation index value consistently appears higher than the actual degradation index value.

[0084] Additionally, the predictive maintenance analysis unit (350) can re-extend the degradation trend by using the updated battery degradation weight and battery degradation rate coefficient as inputs to the predictive maintenance model, and recalculate the time of reaching the degradation threshold for the re-extended degradation trend to re-predict the time of failure. The predictive maintenance analysis unit (350) can repeatedly perform error analysis, parameter update, and the process of re-predicting the time of failure to converge to a degradation trend that matches the actual battery state data, and can determine the time of failure converged as a result of the repeated execution as the final predicted value of failure.

[0085] The operation linkage sharing unit (370) can predict when maintenance is needed for the shared electric mobility vehicle (120) based on the remaining lifespan of the battery or the time of failure, and can share vehicle predictive maintenance operations linked to user accounts by setting vehicle usage restrictions at the time of maintenance needed to determine whether to inspect and replace the battery. The operation linkage sharing unit (370) can quantitatively calculate the time when maintenance must be performed before the battery performance exceeds an acceptable range by using the predicted value of the remaining battery lifespan or the predicted value of the time of failure provided by the predictive maintenance analysis unit (350). Based on the calculated time when maintenance is needed, the operation linkage sharing unit (370) can determine when battery inspection or battery replacement is needed by comparing the available vehicle operating time, vehicle reservation schedule, and usage records per user account.

[0086] Here, the operation linkage sharing unit (370) can generate control commands that limit the vehicle's rental allowance time, travel distance, or driving time in order to apply vehicle usage restrictions at a determined time when maintenance is needed. The operation linkage sharing unit (370) can transmit the generated control commands to a user terminal (110) linked to a user account to clearly provide information that vehicle usage is restricted after the time when maintenance is needed. Additionally, the operation linkage sharing unit (370) can transmit driving instruction information necessary to retrieve the vehicle or move it to a maintenance point where battery inspection or battery replacement is possible during the period when vehicle usage restrictions are applied to the operation system. By providing the user with the predicted time when maintenance is needed and vehicle usage restriction information in this manner, the operation linkage sharing unit (370) can process the vehicle predictive maintenance operation to be shared in real-time based on the user account.

[0087] In one embodiment, the operation linkage sharing unit (370) can share vehicle predictive maintenance operations by notifying the user of the remaining usage time due to vehicle usage restrictions based on the maintenance required time, and when the maintenance required time has passed, providing priority guidance on the location information of a mobility station that the user can select during the movement of the shared electric mobility vehicle (120). The operation linkage sharing unit (370) can calculate the remaining available usage time until the vehicle usage restriction is applied based on the maintenance required time calculated by the predictive maintenance analysis unit (350), and transmit the calculated remaining usage time to the user terminal (110) to guide the user to adjust their vehicle usage plan in advance. In the process of displaying the remaining usage time on the user terminal (110), the operation linkage sharing unit (370) can process the time value so that it is continuously updated according to the battery degradation progress status and real-time operation information, thereby providing the user with clear awareness of the time when the vehicle usage restriction is applied.

[0088] Additionally, when the time for maintenance arrives, the operation linkage sharing unit (370) can search for mobility stations accessible to the user based on the current location information, direction of movement information, and surrounding geographical information of the shared electric mobility vehicle (120). The operation linkage sharing unit (370) sorts mobility stations where maintenance or battery replacement is possible among the searched mobility stations according to priority criteria, and provides location information of the sorted mobility stations to the user terminal (110) to guide the user to select one while driving. The operation linkage sharing unit (370) can support the user in quickly selecting a mobility station where maintenance is possible by providing information on the estimated travel time to the mobility station, traffic flow along the driving route, congestion level of the mobility station, and maintenance availability status.

[0089] Through this guidance procedure, the operation linkage sharing unit (370) can clearly convey to the user information that vehicle use is restricted after the time when maintenance is required, and can share vehicle predictive maintenance operations based on the user account by linking information between the user and the operation system so that the shared electric mobility vehicle (120) can be maintained or battery replaced at an appropriate time.

[0090] In one embodiment, the operation linkage sharing unit (370) may include a function to predict the time when maintenance is required for the shared electric mobility vehicle (120) based on the remaining lifespan of the battery or the time of failure, and to predict the availability of resources required for maintenance along a time axis and to automatically generate a maintenance schedule by reflecting the prediction results. The operation linkage sharing unit (370) may receive maintenance resource data from the operation server, including information on the deployment of maintenance personnel at the mobility station, the availability of battery replacement equipment, the length of the maintenance queue, and statistics on maintenance throughput by time period, and may analyze the received maintenance resource data to calculate the maintenance possibility for each station at a future point in time as a probability value or a quantitative indicator. The operation linkage sharing unit (370) may select the time period and station most suitable for performing maintenance by combining the maintenance possibility for each station at a future point in time with the time when maintenance is required and the quantitative indicator.

[0091] Additionally, the operation linkage sharing unit (370) can adjust the vehicle usage restriction time based on the maintenance availability time of the selected station and automatically generate a maintenance schedule block for performing maintenance and save it to the user account. If the generated maintenance schedule block conflicts with the reservation record or vehicle usage pattern of the user account, the operation linkage sharing unit (370) can determine whether there is a conflict based on the priority of the maintenance schedule block, recalculate the adjusted maintenance availability time, and provide it to the user terminal (110). The operation linkage sharing unit (370) can generate and transmit a control command to perform vehicle usage restriction control during the maintenance time by linking the adjusted maintenance schedule with the vehicle control system.

[0092] In one embodiment, the status data may include not only battery status data but also abnormal current, vibration, thermal status, and fault code information of the motor, inverter, reduction gear, and drivetrain control unit. Here, the fault code information may correspond to a diagnostic code indicating that a predefined error condition has occurred in the motor, inverter, reduction gear, or drivetrain control unit, and may correspond to, for example, code information for identifying an overcurrent occurrence, a prolonged overheating state, a sensor signal abnormality, a control response delay, or a driving failure state. The status data may be used to determine how battery degradation or drivetrain abnormalities occur in conjunction with vehicle operating conditions by storing battery status data and drivetrain status data aligned according to the same time standard and analyzing the correlation between each status data.

[0093] The control unit (390) controls the overall operation of the operation-linked predictive maintenance device (130) and can manage the control flow or data flow between the battery operation profile processing unit (310), the battery status profile processing unit (330), the predictive maintenance analysis unit (350), and the operation-linked sharing unit (370).

[0095] FIG. 4 is a flowchart illustrating the functional configuration of an operation-linked predictive maintenance device based on battery status data of shared electric mobility according to the present invention.

[0096] Referring to FIG. 4, the operation-linked predictive maintenance device (130) can perform authentication for a user account through the battery operation profile processing unit (310) and manage a battery operation profile including the battery maintenance history of a shared electric mobility vehicle (120) linked to the user account (step S410). Here, the operation-linked predictive maintenance device (130) can determine driving habits including the user's acceleration frequency, deceleration pattern, or driving duration through linkage with the user account and calculate the battery degradation weight of the predictive maintenance model by reflecting the driving habits in the battery maintenance history.

[0097] Additionally, the operation-linked predictive maintenance device (130) can manage a battery status profile including the battery's charge state, discharge pattern, and degradation indicator based on battery status data collected from the shared electric mobility vehicle (120) based on the battery status profile processing unit (330) (step S430). Here, the operation-linked predictive maintenance device (130) can calculate a discharge pattern based on the discharge power change rate relative to the discharge time based on the charge state, and calculate a battery degradation rate coefficient of the predictive maintenance model by reflecting the discharge pattern in the degradation indicator.

[0098] The operation-linked predictive maintenance device (130) can predict the remaining lifespan of the battery or the time of failure by inputting the battery operation profile and the battery status profile into the predictive maintenance model based on the predictive maintenance analysis unit (350) (step S450). Here, the operation-linked predictive maintenance device (130) can improve the accuracy of predicting the remaining lifespan of the battery by using a multi-parameter predictive maintenance model that processes the battery degradation weight and the battery degradation rate coefficient of the predictive maintenance model by separating them into different input dimensions.

[0099] Additionally, the operation-linked predictive maintenance device (130) can share vehicle predictive maintenance operations linked to a user account by setting a vehicle usage restriction at the time of maintenance required to determine whether to inspect and replace the battery, based on the remaining lifespan of the battery or the time of failure of the operation-linked sharing unit (370). Here, the operation-linked predictive maintenance device (130) can share vehicle predictive maintenance operations linked to a user account by notifying the user of the remaining usage time based on the vehicle usage restriction at the time of maintenance required, and when the time of maintenance required has passed, it can share vehicle predictive maintenance operations by first providing location information of a mobility station that the user can select during the movement of the shared electric mobility vehicle (120).

[0101] FIG. 5 is a diagram illustrating an information linkage structure between a user terminal and a shared electric mobility vehicle according to an embodiment of an operation-linked predictive maintenance device.

[0102] Referring to FIG. 5, the operation-linked predictive maintenance device (130) relays all operation information and battery status information exchanged between the user terminal (110) and the shared electric mobility vehicle (120), and can transmit the calculated remaining battery life, predicted failure time, and maintenance time information to the user terminal (110) and the shared electric mobility vehicle (120), respectively. The operation-linked predictive maintenance device (130) can immediately transmit the information to the user terminal (110) when the degree of battery degradation increases rapidly during vehicle operation, thereby directly notifying the user of the possibility of dangerous operation.

[0103] Additionally, the operation-linked predictive maintenance device (130) receives vehicle usage requests, reservation schedules, user account information, and estimated driving distances from the user terminal (110), and can determine whether driving requested by the user is possible relative to the remaining battery life based on the received information. If the driving distance requested by the user exceeds the predicted remaining life, the operation-linked predictive maintenance device (130) can provide driving restriction information or alternative vehicle recommendation information to the user terminal (110). The operation-linked predictive maintenance device (130) can adjust the timing of maintenance requirements and vehicle allocation policies by considering the time of the vehicle usage request, the user account grade, usage frequency, etc.

[0104] In one embodiment, the operation-linked predictive maintenance device (130) can receive battery voltage, current, temperature, charge status, internal resistance, accumulated mileage, and GPS-based location data, etc., in real time from the shared electric mobility vehicle (120). The operation-linked predictive maintenance device (130) can update the battery degradation trend extrapolation result based on the received data and reflect the updated battery degradation trend extrapolation result in the operation control logic of the shared electric mobility vehicle (120) to determine whether to restrict the operation of the shared electric mobility vehicle (120), the time when maintenance is required, and the time when the battery is replaced. When the operation-linked predictive maintenance device (130) determines that the shared electric mobility vehicle (120) is approaching the time of failure, it can generate and transmit a control command to the shared electric mobility vehicle (120) to forcibly restrict the operation of the shared electric mobility vehicle (120) or to automatically return the shared electric mobility vehicle (120) to a maintenance base.

[0105] The operation-linked predictive maintenance device (130) can transmit a vehicle usage restriction order, a battery replacement order, or a maintenance priority assignment order to the shared electric mobility vehicle (120) when the time for maintenance of the shared electric mobility vehicle (120) arrives, and provide the relevant fact to the user terminal (110) in the form of a notification so that the vehicle predictive maintenance operation can be shared in real time. Even after the vehicle usage restriction is applied, the operation-linked predictive maintenance device (130) can monitor the vehicle's movement path, stopping location, and speed changes to adjust the intensity of the operation restriction so that the user cannot operate the vehicle arbitrarily.

[0106] For example, the operation-linked predictive maintenance device (130) can provide a push notification indicating when maintenance is needed at the top of the screen of the user terminal (110) so that the user can immediately recognize when maintenance is needed. In addition, the operation-linked predictive maintenance device (130) can provide a warning banner indicating when maintenance is needed on the lock screen of the user terminal (110) so that the user can check the maintenance information even without unlocking the terminal.

[0107] Additionally, the operation-linked predictive maintenance device (130) can provide a pop-up window containing the remaining driving time, the distance remaining until maintenance is needed, and a summary of the battery status on the home screen or driving screen of an application installed on the user terminal (110), so that the user can clearly check the current vehicle status and the degree of maintenance required. When the voice guidance function is activated on the user terminal (110), the operation-linked predictive maintenance device (130) can output the fact that the time for maintenance has arrived in the form of a voice message, thereby audibly conveying the maintenance requirement information to the user while driving.

[0108] Additionally, the operation-linked predictive maintenance device (130) can utilize the vibration function of the user terminal (110) to output the arrival of the time when maintenance is needed as a specific vibration pattern, and can provide the user with the ability to recognize the information regarding the need for maintenance through a tactile signal even if the user has not recognized a visual or voice notification. The operation-linked predictive maintenance device (130) can store a text notification containing the time when maintenance is needed, the reason for maintenance, battery health, and a list of nearby mobility stations available for maintenance in the notification center or message inbox of the user terminal (110), so that the user can repeatedly check the notification content.

[0110] Although the present invention has been described above with reference to preferred embodiments, those skilled in the art will understand that various modifications and changes can be made to the invention without departing from the spirit and scope of the invention as described in the following claims. Explanation of the symbols

[0112] 100: Operation-linked predictive maintenance system 110: User terminal 120: Shared electric mobility vehicles 130: Operation-linked predictive maintenance device 150: Database 210: Processor 230: Memory 250: User I / O Section 270: Network I / O Section 290: Communication port section 310: Battery Operation Profile Processing Unit 330: Battery Status Profile Processing Unit 350: Predictive Maintenance Analysis Department 370: Operations Linkage Sharing Department 390: Control unit

Claims

Claim 1 A battery operation profile processing unit that performs authentication for a user account, manages a battery operation profile including the battery maintenance history of a shared electric mobility vehicle linked to the user account, determines driving habits including the user's acceleration frequency, deceleration pattern, or driving duration through linkage with the user account, and calculates a battery degradation weighting of a predictive maintenance model by reflecting the driving habits in the battery maintenance history; a battery status profile processing unit that manages a battery status profile including the battery's charge state, discharge pattern, and degradation indicator based on battery status data collected from the shared electric mobility vehicle, calculates the discharge pattern based on the rate of change of discharge power relative to discharge time based on the charge state, and calculates a battery degradation rate coefficient of the predictive maintenance model by reflecting the discharge pattern in the degradation indicator; and a predictive maintenance analysis unit that inputs the battery operation profile and the battery status profile into a predictive maintenance model to predict the remaining lifespan or failure time of the battery.The system includes an operation linkage sharing unit that shares a vehicle predictive maintenance operation linked to the user account by setting a vehicle usage restriction at the time of maintenance required to determine whether to inspect and replace the battery, based on the remaining lifespan or failure time of the battery, predicting the time of maintenance required for the shared electric mobility vehicle based on the remaining lifespan or failure time of the battery, and comparing the vehicle operating time, vehicle reservation schedule, and usage records per user account based on the time of maintenance required. The operation linkage sharing unit notifies the user of the user account of the remaining usage time due to the vehicle usage restriction based on the time of maintenance required, and when the time of maintenance required has elapsed, prioritizes providing location information of mobility stations selectable by the user during the movement of the shared electric mobility vehicle to share the vehicle predictive maintenance operation; adjusts the vehicle usage restriction time based on the maintenance availability time of the selected station; automatically generates a maintenance schedule block for performing maintenance and saves it to the user account; if the maintenance schedule block conflicts with the reservation record or vehicle usage pattern of the user account, recalculates the adjusted maintenance availability time; and reflects the vehicle usage restriction state set according to the predictive maintenance analysis result to the operation system. Operation-linked predictive maintenance device based on battery status data of shared electric mobility, characterized by controlling whether an electric mobility vehicle is an operation target or its operation status. Claim 2 delete Claim 3 delete Claim 4 An operation-linked predictive maintenance device based on battery status data of shared electric mobility, wherein, in claim 1, the predictive maintenance analysis unit improves the prediction accuracy of the remaining life of the battery by utilizing a multi-parameter predictive maintenance model that processes the battery degradation weight and battery degradation rate coefficient of the predictive maintenance model by separating them into different input dimensions. Claim 5 An operation-linked predictive maintenance device based on battery status data of shared electric mobility, wherein, in claim 4, the predictive maintenance analysis unit predicts the time of failure of the battery by extrapolating the battery degradation trend on the time axis using the battery degradation rate coefficient and correcting the extrapolated degradation trend according to user driving habits using the battery degradation weight. Claim 6 delete Claim 7 An operation-linked predictive maintenance device based on battery status data of shared electric mobility, characterized in that, in claim 1, the status data includes not only the battery status data but also abnormal current, vibration, thermal status, and fault code information of the motor, inverter, reduction gear, and drive system control unit.

Images