Apparatus and method for predicting SOH of battery

Abstract

The present invention relates to an apparatus and a method for predicting SOH of a battery, in which the apparatus includes a training data set including battery information, driving information, and SOH of a probe vehicle, training an artificial intelligence (AI) model by using the training data set, and predicting SOH of the battery. And predicting an SOH of the battery corresponding to the battery information and the driving information of the target vehicle based on the AI model, thereby predicting the SOH of the battery provided in the target vehicle at a predetermined accuracy.

Description

[0001] Cross - reference to related applications

[0002] This application claims the priority of Korean Patent Application No. 10 - 2023 - 0186229, filed on December 19, 2023, the entire content of which is incorporated herein for all purposes by this reference. Technical field

[0003] The present invention relates to a technique for predicting the state of health (SOH) of a battery based on an artificial neural network model. Background art

[0004] Generally, an artificial neural network (ANN) in the field of artificial intelligence is an algorithm that enables a machine to learn by simulating the human neural structure. Recently, it has been applied to image recognition, speech recognition, natural language processing, etc., and has shown excellent results. An artificial neural network includes an input layer that receives inputs, a hidden layer that actually learns, and an output layer that returns the result of an operation. An artificial neural network including multiple hidden layers is called a deep neural network (DNN), which is also a type of artificial neural network.

[0005] An artificial neural network allows a computer to learn on its own based on data. When attempting to solve a problem using an artificial neural network, an appropriate artificial neural network model and data to be analyzed need to be prepared. The artificial neural network model for solving the problem is trained based on the data. Before training the model, the data needs to be appropriately processed first. This is because the input data and output data required by the artificial neural network model are standardized. Therefore, a process is required to pre - process the acquired raw data to match the requested input data. After the pre - processing is completed, the processed data should be divided into two categories. That is, the data should be divided into a training data set and a validation data set. The training data set is used to train the model, and the validation data set is used to verify the performance of the model.

[0006] There are various reasons for validating an artificial neural network model. Artificial neural network developers adjust the model by modifying the hyperparameters of the model based on the validation results of the model. In addition, model validation is performed to select a suitable model from various models. The reasons for the need for model validation are explained in more detail below.

[0007] First is the prediction accuracy. As a result, the aim of the artificial neural network is to obtain good performance on out-of-sample data that was not used for training. Therefore, after generating the model, it is necessary to check how the model performs on out-of-sample data. However, since the training dataset should not be used to validate the model, a validation dataset separated from the training dataset should be used to measure the accuracy of the model.

[0008] Second is to enhance the performance of the model by adjusting the model. For example, overfitting can be prevented. Overfitting means that the model is over-trained on the training dataset. For example, in the case where the training accuracy is high but the validation accuracy is low, overfitting can be suspected. In addition, it can be understood in more detail through the training loss and the validation loss. When overfitting occurs, it is necessary to prevent overfitting to improve the validation accuracy. Overfitting can be prevented by utilizing schemes such as regularization or dropout.

[0009] Meanwhile, conventional techniques for predicting the SOH of a battery predict SOHc based on the capacity of the battery, predict SOHr based on the resistance of the battery, and predict the final SOH based on SOHc and SOHr.

[0010] Such existing techniques only utilize battery information to predict the SOH, so the prediction accuracy is low.

[0011] The information included in the background art of the present invention is only intended to enhance the overall understanding of the present invention, and should not be regarded as an admission or any form of implication that this information constitutes prior art known to those skilled in the art. Summary of the Invention

[0012] Aspects of the present invention aim to provide a device and method for predicting the state of health (SOH) of a battery, configured to predict the SOH of a battery provided in a target vehicle with high accuracy by including a training dataset (the training dataset includes battery information, driving information, and SOH of a probe vehicle), training an artificial intelligence (AI) model by utilizing the training dataset, and predicting the SOH of the battery corresponding to the battery information and driving information of the target vehicle based on the AI model.

[0013] Another aspect of the present invention provides a device and method for predicting the SOH of a battery, configured to predict the SOH of a battery provided in a target vehicle with high accuracy by including an AI model (the AI model learns the SOH corresponding to the battery information and driving information of a probe vehicle), and predicting the SOH of the battery corresponding to the battery information and driving information of the target vehicle based on the AI model.

[0014] Another aspect of the present invention provides an apparatus and method for predicting the state of health (SOH) of a battery, which are configured to predict the SOH of a battery provided in a target vehicle with high accuracy by including a training data set (the training data set includes battery information, driving information, and SOH of a probe vehicle), train an AI model by using the training data set, predict a first SOH of the battery corresponding to the battery information and driving information of the target vehicle based on the AI model, obtain a second SOH from a battery management system (BMS) provided in the target vehicle, and correct the first SOH by using the second SOH state.

[0015] Another aspect of the present invention provides an apparatus and method for predicting the state of health (SOH) of a battery, which are configured to predict the SOH of a battery provided in a target vehicle with high accuracy by including an AI model (which learns the SOH corresponding to the battery information and driving information of a probe vehicle), predict a first SOH of the battery corresponding to the battery information and driving information of the target vehicle based on the AI model, obtain a second SOH from a battery management system (BMS) provided in the target vehicle, and correct the first SOH by using the second SOH.

[0016] The technical problems solved by the present invention are not limited to the above problems, and those skilled in the art to which the present invention pertains will clearly understand any other technical problems not mentioned herein from the following description. In addition, it can be easily understood that the objects and advantages of the present invention can be achieved by the units and combinations thereof recited in the claims.

[0017] According to an aspect of the present invention, an apparatus for predicting the state of health (SOH) of a battery, the apparatus includes a storage device and a controller, the storage device stores an SOH prediction model, and the controller predicts a first SOH of a battery provided in a target vehicle based on the SOH prediction model, wherein the controller may be configured to predict the first SOH by using at least one of the vehicle speed and cumulative mileage of the target vehicle and the voltage, current, temperature, and number of charging times of the battery in the target vehicle.

[0018] According to an exemplary embodiment of the present invention, the controller trains the SOH prediction model by using a training data set, and the training data set includes battery information, driving information, and SOH of a battery in a probe vehicle.

[0019] According to an exemplary embodiment of the present invention, the battery information may include at least one or a combination of voltage, current, temperature, number of rapid charging times, and number of slow charging times of a battery in a probe vehicle.

[0020] According to an exemplary embodiment of the present invention, the driving information may include at least one of vehicle speed, cumulative mileage, and driving time, or a combination thereof.

[0021] According to an exemplary embodiment of the present invention, the controller may obtain a second SOH of a battery provided in a target vehicle from a battery management system (BMS) through a vehicle network, and correct the first SOH by using the second SOH.

[0022] According to an exemplary embodiment of the present invention, when the first SOH of a battery provided in a target vehicle exceeds a threshold range, the controller may obtain a second SOH of the battery provided in the target vehicle from the BMS.

[0023] According to an exemplary embodiment of the present invention, the controller may be configured to determine the reliability of the first SOH based on the degree to which the first SOH of a battery provided in a target vehicle deviates from a threshold range, and when the reliability does not exceed a threshold, obtain a second SOH of the battery provided in the target vehicle from the BMS.

[0024] According to an exemplary embodiment of the present invention, the controller may be configured to determine a reflection rate of the second SOH based on the reliability when correcting the first SOH by using the second SOH.

[0025] According to another aspect of the present invention, a method for predicting a state of health (SOH) of a battery includes storing an SOH prediction model by a storage device, and predicting a first SOH of a battery provided in a target vehicle by a controller based on the SOH prediction model, wherein predicting the first SOH includes predicting, by the controller, the first SOH by using at least one of a vehicle speed and a cumulative mileage of the target vehicle and a voltage, a current, a temperature, and a number of charging times of the battery in the target vehicle.

[0026] According to an exemplary embodiment of the present invention, storing the SOH prediction model may further include training the SOH prediction model by the controller by using a training data set (the training data set includes battery information, driving information, and SOH of a battery of a detection vehicle).

[0027] According to an exemplary embodiment of the present invention, the battery information may include at least one of a voltage, a current, a temperature, a number of fast charging times, and a number of slow charging times in a battery of a detection vehicle, or a combination thereof.

[0028] According to an exemplary embodiment of the present invention, the driving information may include at least one of vehicle speed, cumulative mileage, and driving time, or a combination thereof.

[0029] According to an exemplary embodiment of the present invention, predicting the first SOH may further include the controller obtaining a second SOH of a battery disposed in a target vehicle from a battery management system (BMS) via a vehicle network, and the controller correcting the first SOH by using the second SOH.

[0030] According to an exemplary embodiment of the present invention, obtaining the second SOH may include: when a first SOH of a battery disposed in a target vehicle exceeds a threshold range, the controller obtaining a second SOH of the battery disposed in the target vehicle from the BMS.

[0031] According to an exemplary embodiment of the present invention, obtaining the second SOH may include: based on the degree to which a first SOH of a battery disposed in a target vehicle deviates from a threshold range, the controller determining the reliability of the first SOH, and when the reliability does not exceed a threshold, the controller obtaining a second SOH of the battery disposed in the target vehicle from the BMS.

[0032] According to an exemplary embodiment of the present invention, correcting the first SOH may further include the controller determining a reflection rate of the second SOH based on the determined reliability.

[0033] According to an aspect of the present invention, a system for predicting a state of health (SOH) of a battery includes: a server that trains an SOH prediction model by using a training data set including battery information, driving information, and SOH of a detection vehicle; and an SOH prediction device that predicts a first SOH of a battery disposed in a target vehicle based on the SOH prediction model, wherein the SOH prediction device is configured to predict the first SOH by using at least one of a vehicle speed and an accumulated mileage of the target vehicle and a voltage, a current, a temperature, and a number of charging times of a battery in the target vehicle.

[0034] The method and apparatus of the present invention have other characteristics and advantages, which will be apparent from or will be described in detail in the accompanying drawings and subsequent detailed description incorporated herein. The accompanying drawings and the detailed description together are used to explain specific principles of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 is a schematic diagram showing a system for predicting the SOH of a battery according to an exemplary embodiment of the present invention;

[0036] Figure 2 is a block diagram showing a configuration of a battery SOH prediction device according to an exemplary embodiment of the present invention;

[0037] Figure 3A block diagram showing a process in which a controller provided in a device for predicting the SOH of a battery according to an exemplary embodiment of the present invention is configured to determine a final SOH by using a first SOH and a second SOH;

[0038] Figure 4 A flowchart showing a method for predicting the SOH of a battery according to an exemplary embodiment of the present invention;

[0039] Figure 5 A block diagram showing a computing system for performing a method for predicting the SOH of a battery according to various exemplary embodiments of the present invention.

[0040] It can be understood that the accompanying drawings are not drawn to scale and are merely appropriately simplified drawings for illustrating the basic principles and various features of the present invention. Specific design features of the present invention disclosed herein, including, for example, specific dimensions, directions, positions, and shapes, will be determined in part by the specific application and use environment.

[0041] In the drawings, throughout the various figures, the same reference numerals represent the same or equivalent parts of the present invention. Detailed Description of the Embodiments

[0042] Reference will now be made in detail to various embodiments of the present invention, examples of which are illustrated and described in the accompanying drawings. Although the present invention will be described in conjunction with the exemplary embodiments of the present invention, it will be understood that this specification is not intended to limit the present invention to those exemplary embodiments. On the contrary, the present invention is intended to cover not only the exemplary embodiments of the present invention but also various alternative embodiments, modified embodiments, equivalent embodiments, and other embodiments that may be included within the spirit and scope of the present invention as defined by the appended claims.

[0043] Hereinafter, various exemplary embodiments of the present invention will be described in detail with reference to the exemplary drawings. When adding reference numerals to the components of each figure, it should be noted that even if the same or equivalent components are shown in other figures, they are denoted by the same reference numerals. In addition, when determining that a detailed description of a related known configuration or function will interfere with the understanding of the exemplary embodiments of the present invention, the detailed description will be omitted.

[0044] In addition, when describing the components of the present invention, terms such as first, second, A, B, (a), (b), etc. may be used herein. The terms provided are only used to distinguish components from other elements, and the nature, order, sequence, and quantity of the elements are not limited by the terms. In addition, unless otherwise defined, all terms (including technical terms or scientific terms) used herein include the same meanings as those commonly understood by those skilled in the art to which the present invention pertains. Terms defined in a general dictionary should be interpreted as having meanings consistent with the context of the related art, and should not be interpreted as ideal or overly formal meanings unless clearly defined in the specification of the present invention.

[0045] Figure 1 is a schematic diagram showing a system for predicting the SOH of a battery according to an exemplary embodiment of the present invention.

[0046] As Figure 1 shown, the system for predicting the SOH of a battery according to an exemplary embodiment of the present invention may include an SOH prediction device 100, a data server 200, and at least one probe vehicle 300.

[0047] In various exemplary embodiments of the present invention, the SOH prediction device 100 may be disposed in a target vehicle, receive a training data set (the training data set includes battery information, driving information, and SOH of the probe vehicle 300), train an AI model by using the training data set, and predict the SOH of the battery corresponding to the battery information and driving information of the target vehicle (i.e., the battery disposed in the target vehicle) based on the AI model.

[0048] In various exemplary embodiments of the present invention, the SOH prediction device 100 may receive a trained AI model from the data server 200, and predict the SOH of the battery corresponding to the battery information and driving information of the target vehicle based on the AI model. In this case, the data server 200 may train the AI model by using a training data set (the training data set includes battery information, driving information, and SOH of the probe vehicle 300).

[0049] In various exemplary embodiments of the present invention, the SOH prediction device 100 may receive a training data set (the training data set includes battery information, driving information, and SOH of the probe vehicle 300) from the data server 200, train an AI model by using the training data set, predict a first SOH of the battery corresponding to the battery information and driving information of the target vehicle (i.e., the battery disposed in the target vehicle) based on the AI model, obtain a second SOH from the BMS disposed in the target vehicle, and correct the first SOH by using the second SOH.

[0050] In various exemplary embodiments of the present invention, the SOH prediction device 100 may receive a trained AI model from the data server 200, predict a first SOH of a battery corresponding to battery information and driving information of a target vehicle based on the AI model, obtain a second SOH from a BMS provided in the target vehicle, and correct the first SOH by using the second SOH.

[0051] In each of the above embodiments, the probing vehicle and the target vehicle have the same specifications, and the battery provided in the probing vehicle and the battery provided in the target vehicle have the same specifications.

[0052] The data server 200 may be configured to generate a training data set (the training data set includes battery information, driving information, and SOH of the probing vehicle 300), and may train the AI model by using the training data set.

[0053] The probing vehicle 300 may periodically send battery information and driving information to the data server 200.

[0054] Figure 2 is a block diagram showing the configuration of a battery SOH prediction device according to an exemplary embodiment of the present invention.

[0055] As Figure 2 shown, the battery SOH prediction device 100 according to an exemplary embodiment of the present invention may include a storage device 10, a communication device 20, a vehicle network interface device 30, and a controller 40. In this case, according to the solution for implementing the battery SOH prediction device 100 according to an exemplary embodiment of the present invention, the components may be combined with each other to be implemented as one, or some components may be omitted.

[0056] Regarding each component, first, the storage device 10 may store a training data set (the training data set includes battery information, driving information, and SOH of the probing vehicle 300). In this case, the driving information of the probing vehicle 300 may include vehicle speed and cumulative mileage, and the battery information of the probing vehicle 300 may include battery voltage, current, temperature, number of charging times (for example, number of fast charging times, number of slow charging times, etc.).

[0057] In addition, the storage device 10 may store various logics, algorithms, and programs that are required in the process of training the AI model by using the training data set and predicting the SOH of a battery (i.e., the battery provided in the target vehicle) corresponding to the battery information and driving information of the target vehicle based on the AI model.

[0058] In addition, the storage device 10 may store various logics, algorithms, and programs that are required in the process of training an AI model by using a training data set, predicting a first SOH of a battery (i.e., a battery provided in the target vehicle) corresponding to the battery information and driving information of the target vehicle based on the AI model, obtaining a second SOH from a BMS provided in the target vehicle, and correcting the first SOH by using the second SOH.

[0059] Meanwhile, the storage device 10 may store a trained AI model (i.e., an SOH prediction model of the battery) that has completed learning.

[0060] The communication device 20 (which is a module that provides a communication interface with the data server 200) may receive a training data set (the training data set includes battery information, driving information, and SOH of the probe vehicle 300) from the data server 200.

[0061] In addition, the communication device 20 may receive a trained AI model from the data server 200.

[0062] The communication device 20 may include at least one of a mobile communication module, a wireless Internet module, and a short-range communication module.

[0063] The mobile communication module may communicate with the data server 200 through a mobile communication network constructed according to a technical standard or communication scheme for mobile communication (e.g., Global System for Mobile Communications (GSM), Code Division Multiple Access (CDMA), Code Division Multiple Access 2000 (CDMA2000), Enhanced Voice Data Optimized or Enhanced Voice Only Data (EV-DO), Wideband CDMA (WCDMA), High-Speed Downlink Packet Access (HSDPA), High-Speed Uplink Packet Access (HSUPA), Long-Term Evolution (LTE), Long-Term Evolution Advanced (LTE-A), etc.).

[0064] The wireless Internet module (which is a module for wireless Internet access) may communicate with the data server 200 through Wireless LAN (WLAN), Wi-Fi, Wi-Fi Direct, Digital Living Network Alliance (DLNA), Wireless Broadband (WiBro), Worldwide Interoperability for Microwave Access (WiMAX), High-Speed Downlink Packet Access (HSDPA), High-Speed Uplink Packet Access (HSUPA), Long-Term Evolution (LTE), Long-Term Evolution Advanced (LTE-A), etc.

[0065] The short-range communication module may communicate with the data server 200 by using Bluetooth TM, at least one of radio frequency identification (RFID), infrared data association (IrDA), ultra-wideband (UWB), ZigBee, near field communication (NFC), and wireless universal serial bus (USB) technologies to support short-range communication with the data server 200.

[0066] The vehicle network interface device 30 (which is a module providing a communication interface with the vehicle network) can periodically receive battery information and driving information from the vehicle network. In addition, the vehicle network interface device 30 can receive the state of health (SOH) of the battery determined by the BMS. In this case, the vehicle network can include Controller Area Network (CAN), Controller Area Network with Flexible Data Rate (CAN FD), Local Interconnect Network (LIN), FlexRay, Media Oriented System Transport (MOST), Ethernet, etc.

[0067] The controller 40 can perform overall control so that each component executes its function. The controller 40 can be implemented in the form of hardware or software, or can be implemented as a combination of hardware and software. The controller 40 can be implemented as a microprocessor, but is not limited thereto.

[0068] The controller 40 can train an AI model by using the training data set stored in the storage device 10, and predict the SOH of the battery corresponding to the battery information and driving information of the target vehicle based on the AI model. In this case, the controller 40 can input the battery information and driving information of the target vehicle obtained from the vehicle network through the vehicle network interface device 30 into the AI model to predict the SOH of the battery corresponding to the battery information and driving information of the target vehicle.

[0069] In this case, the driving information of the target vehicle can include vehicle speed and cumulative mileage, and the battery information of the target vehicle can include battery voltage, current, temperature, number of charging times (e.g., number of fast charging times, number of slow charging times, etc.).

[0070] As a reference, the battery pack includes a preset number of groups. In the groups, a plurality of battery cells are connected in parallel with each other to increase the current capacity, and the battery pack includes a structure in which the groups are connected in series with each other to output a rated voltage. In this case, the battery cell includes a positive electrode current collector, a negative electrode current collector, a separator, an active material, an electrolyte, etc., and is configured to repeatedly charge and discharge through an electrochemical reaction between components. To protect the plurality of battery cells from external shocks such as heat, vibration, etc., a battery module can be formed by combining a plurality of battery cells into one. To systematically manage a plurality of battery modules, a battery pack (i.e., a battery system) can be formed by using a plurality of battery modules, a battery management system (BMS), and a cooling device.

[0071] Therefore, the battery information of the vehicle may be one of cell information, battery module information, and battery pack information. Specifically, the voltage, current, and temperature of the vehicle's battery may include the voltage, current, and temperature of one of the battery cells, battery modules, and battery packs.

[0072] The controller 40 may train the AI model by using the training data set stored in the storage device 10, predict the first SOH corresponding to the battery information and driving information of the target vehicle based on the AI model, obtain the second SOH from the BMS provided in the target vehicle, and correct the first SOH by using the second SOH.

[0073] In this case, it may be preferable that when the first SOH exceeds the threshold range, the controller 40 obtains the second SOH from the BMS through the vehicle network and corrects the first SOH by using the second SOH. In this case, when the first SOH does not exceed the threshold range, the controller 40 may be configured to determine the first SOH as the final SOH of the battery provided in the target vehicle.

[0074] In addition, the controller may be configured to determine the reliability of the first SOH based on the degree to which the first SOH deviates from the threshold range, and when the reliability does not exceed the threshold (e.g., 95%), obtain the second SOH from the BMS through the vehicle network.

[0075] As an exemplary embodiment of the present invention, when the first SOH predicted by the AI model is 85% and the preset threshold range is 79% to 80%, the controller 40 may be configured to determine the reliability of the first SOH as 94.1% (≈8000 / 85). For reference, the threshold range may be determined in advance by considering the driving time of the target vehicle, the battery usage amount (Ah or kWh), and the number of charging times.

[0076] As an exemplary embodiment of the present invention, when the first SOH predicted by the AI model is 90% and the preset threshold range is 79% to 80%, the controller 40 may be configured to determine the reliability of the first SOH as 88.8% (≈8000 / 90).

[0077] As another example, when the first SOH predicted by the AI model is 75% and the preset threshold range is 79% to 80%, the controller 40 may be configured to determine the reliability of the first SOH as 94.9% (≈7500 / 79).

[0078] As another example, when the first SOH predicted by the AI model is 65% and the preset threshold range is 79% to 80%, the controller 40 may be configured to determine the reliability of the first SOH as 82.2% (≈6500 / 79).

[0079] Meanwhile, when the reliability of the first SOH does not exceed, for example, 95%, the controller 40 can obtain the second SOH from the BMS via the vehicle network. The controller 40 can be configured to determine the reflection rate of the second SOH corresponding to the reliability of the first SOH based on, for example, Table 1 below.

[0080] [Table 1]

[0081] Reliability of the first SOH Reflection rate of the second SOH 90% to 95% 30％ 85% to 90% 50％ 85% or less 100％

[0082] In Table 1, when the reliability of the first SOH is 94%, the final SOH can be determined by reflecting 70% of the first SOH and 30% of the second SOH. When the reliability of the first SOH is 89%, the final SOH can be determined by reflecting 50% of the first SOH and 50% of the second SOH. When the reliability of the first SOH is 85% or lower, the first SOH can not be reflected at all, and the second SOH can be determined as the final SOH.

[0083] For example, when the first SOH is 90% and the second SOH is 70%, the reliability of the first SOH is 88.8%, such that 50% of the first SOH is reflected and 50% of the second SOH is reflected to determine the final SOH. That is, the controller 40 can be configured to determine the final SOH as 80% (=90% / 2 + 70% / 2).

[0084] Figure 3 is a block diagram showing a process in which a controller provided in a device for predicting the SOH of a battery according to an exemplary embodiment of the present invention is configured to determine a final SOH by using a first SOH and a second SOH.

[0085] As Figure 3 shown, the AI model 310 predicts a first SOH of a battery provided in a target vehicle, and the BMS 320 predicts a second SOH of the battery provided in the target vehicle.

[0086] Therefore, in 311, the controller 40 is configured to determine the reliability of the first SOH, and is configured to determine the reflection rate of the first SOH based on the reliability of the first SOH. In addition, the controller 40 is configured to determine the reflection rate of the second SOH in 321.

[0087] Therefore, in 330, the controller 40 can be configured to determine the final SOH based on the reflection rate of the first SOH and the reflection rate of the second SOH.

[0088] Figure 4 is a flowchart showing a method for predicting the SOH of a battery according to an exemplary embodiment of the present invention.

[0089] First, in step 401, the storage device 10 stores the SOH prediction model.

[0090] Accordingly, in step 402, the controller 40 predicts a first SOH of a battery provided in a target vehicle based on the SOH prediction model. In this case, the SOH prediction model is a model trained based on a training data set (the training data set including battery information, driving information, and SOH of a probe vehicle). In this case, the controller 40 may be configured to predict the first SOH by using at least one of a vehicle speed and an accumulated mileage of the target vehicle and a voltage, a current, a temperature, and a number of charging times of the battery.

[0091] In addition, the controller 40 may control the target vehicle to warn a user when the first SOH is lower than a threshold. For example, the controller 40 may send a warning signal to a combination instrument panel in the target vehicle via a vehicle network.

[0092] Figure 5 is a block diagram of a computing system for performing a method of predicting an SOH of a battery according to various exemplary embodiments of the present invention.

[0093] Refer to Figure 5 , the method of predicting an SOH of a battery according to the above exemplary embodiment of the present invention may be implemented by a computing system 1000. The computing system 1000 may include at least one processor 1100, a memory 1300, a user interface input device 1400, a user interface output device 1500, a storage device 1600, and a network interface 1700 connected via a system bus 1200.

[0094] The processor 1100 may be a central processing unit (CPU) or a semiconductor device for processing instructions stored in the memory 1300 and / or the storage device 1600. The memory 1300 and the storage device 1600 may include various types of volatile or non-volatile storage media. For example, the memory 1300 may include a read-only memory (ROM) 1310 and a random access memory (RAM) 1320.

[0095] Accordingly, the processes of the methods or algorithms described in connection with the exemplary embodiments of the present invention may be implemented directly by hardware, software modules, or a combination thereof executed by the processor 1100. The software modules may reside in a storage medium (i.e., the memory 1300 and / or the memory 1600), such as RAM, flash memory, ROM, EPROM, EEPROM, registers, a hard disk, a solid state drive (SSD), a removable disk, or a CD-ROM. The exemplary storage medium is coupled to the processor 1100, and the processor 1100 can read information from the storage medium and can write information to the storage medium. In another approach, the storage medium may be integrated with the processor 1100. The processor 1100 and the storage medium may reside in an application specific integrated circuit (ASIC). The ASIC may reside within a user terminal. In another approach, the processor 1100 and the storage medium may reside as separate components within the user terminal.

[0096] In various exemplary embodiments of the present invention, the above-described respective operations may be performed by a control device, and the control device may be configured by a plurality of control devices or an integrated single control device.

[0097] In various exemplary embodiments of the present invention, the memory and the processor may be provided as one chip or as separate chips.

[0098] In various exemplary embodiments of the present invention, the scope of the present invention includes software or machine-executable commands (e.g., an operating system, an application program, firmware, a program, etc.) for enabling the operations of the methods according to the various embodiments to be executed on a device or a computer, and a non-transitory computer-readable medium including such software or commands stored thereon and executable on the device or the computer.

[0099] Furthermore, terms such as "unit" and "module" included in the specification denote a unit for performing at least one function or operation, and may be implemented by hardware, software, or a combination thereof.

[0100] In an exemplary embodiment of the present invention, a vehicle may be referred to as being based on a concept including various means of transportation. In some cases, a vehicle may be interpreted as being based on a concept that includes not only various land vehicles traveling on roads, such as cars, motorcycles, trucks, and buses, but also various means of transportation, such as airplanes, drones, ships, etc.

[0101] For purposes of facilitating explanation and precisely defining the appended claims, the terms "upper", "lower", "inner", "outer", "above", "below", "upward", "downward", "front", "rear", "back", "inner", "outer", "inward", "outward", "internal", "external", "inner side", "outer side", "forward", "backward" are used to describe the features of the exemplary embodiments with reference to the positions of these features shown in the accompanying drawings. It will be further understood that the term "connected" or its derivatives refer to both direct connection and indirect connection.

[0102] The term "and / or" may include combinations of multiple related listed items or any one of the multiple related listed items. For example, "A and / or B" includes all three cases, such as "A", "B", and "A and B".

[0103] In the exemplary embodiments of the present invention, "at least one of A and B" may refer to "at least one of A or B" or "at least one of the combinations of at least one of A and B". In addition, "one or more of A and B" may refer to "one or more of A or B" or "one or more of the combinations of one or more of A and B".

[0104] In this document, unless otherwise specified, the singular includes the plural, unless the context clearly indicates otherwise.

[0105] In the exemplary embodiments of the present invention, it should be understood that terms such as "including" or "having" may be intended to mean that there may be features, quantities, steps, operations, elements, components, or combinations thereof described in the specification, and do not exclude the possibility of adding or existing one or more other features, quantities, steps, operations, elements, components, or combinations thereof.

[0106] According to the exemplary embodiments of the present invention, components may be combined with each other to be implemented as one, or some components may be omitted.

[0107] The foregoing description of the specific exemplary embodiments of the present invention has been presented for purposes of illustration and description. They are not intended to be exhaustive or to limit the invention to the precise forms disclosed, and obviously many modifications and changes are possible in light of the above teachings. The exemplary embodiments were chosen and described in order to explain the particular principles of the invention and its practical application so that others skilled in the art may implement and utilize the various exemplary embodiments of the invention and their various alternative forms and modifications. The scope of the invention is intended to be defined by the appended claims and their equivalents.

Claims

1. A device for predicting the health status of a battery, the device comprising: a storage device configured to store a health status prediction model; as well as a controller operably connected to the storage device and configured to predict a first state of health of a battery provided in a target vehicle based on a state of health prediction model, The controller is further configured to predict the first health state by utilizing the speed and accumulated mileage of the target vehicle and at least one of the voltage, current, temperature and number of charging times of the battery in the target vehicle.

2. The device for predicting the health status of a battery according to claim 1, wherein: The controller is further configured to train a health state prediction model by using a training data set, the training data set including battery information of a battery in the detection vehicle, driving information of the detection vehicle, and a health state of the battery in the detection vehicle.

3. The device for predicting the health status of a battery according to claim 2, wherein: The battery information includes detecting at least one of a voltage, a current, a temperature, a number of fast charges, a number of slow charges, or a combination thereof in a battery of the vehicle.

4. The device for predicting the health status of a battery according to claim 2, wherein: The driving information includes at least one of the speed, accumulated mileage, and driving time of the detection vehicle, or a combination thereof.

5. The device for predicting the health status of a battery according to claim 1, wherein: The controller is further configured to acquire a second state of health of a battery provided in the target vehicle from a battery management system through a vehicle network, and correct the first state of health by using the second state of health.

6. The device for predicting the health status of a battery according to claim 5, wherein: The controller is further configured to obtain a second state of health of a battery disposed in the target vehicle from a battery management system in response to a first state of health of a battery disposed in the target vehicle exceeding a threshold range.

7. The device for predicting the health status of a battery according to claim 5, wherein: The controller is further configured to determine the reliability of the first health state of the battery set in the target vehicle based on the degree to which the first health state of the battery set in the target vehicle deviates from a threshold range, and in response to the reliability not exceeding the threshold, obtain a second health state of the battery set in the target vehicle from the battery management system.

8. The device for predicting the health status of a battery according to claim 7, wherein: The controller is further configured to determine a reflection rate of the second health state based on reliability in a case where the first health state is corrected by using the second health state.

9. A method for predicting the health status of a battery, the method comprising: The health status prediction model is stored by a storage device; predicting, by a controller operably connected to the storage device, a first state of health of a battery provided in a target vehicle based on a state of health prediction model, Among them, predicting the first health state of the battery set in the target vehicle includes: predicting the first health state by the controller by utilizing the vehicle speed and accumulated mileage of the target vehicle and at least one of the voltage, current, temperature and number of charging times of the battery in the target vehicle.

10. The method according to claim 9, wherein: Storing the health state prediction model further includes training the health state prediction model by the controller by using a training data set, wherein the training data set includes battery information of the battery in the detection vehicle, driving information of the detection vehicle, and the health state of the battery in the detection vehicle.

11. The method according to claim 10, wherein: The battery information includes detecting at least one of a voltage, a current, a temperature, a number of fast charges, a number of slow charges, or a combination thereof in a battery of the vehicle.

12. The method according to claim 10, wherein: The driving information includes at least one of the speed, accumulated mileage, and driving time of the detection vehicle, or a combination thereof.

13. The method according to claim 9, wherein: Predicting the first health state further includes: Acquiring, by the controller, a second health status of a battery disposed in the target vehicle from a battery management system via a vehicle network; The first state of health is corrected by the controller by utilizing the second state of health.

14. The method according to claim 13, wherein: Acquiring a second health state of a battery disposed in the target vehicle includes: in response to a first health state of the battery disposed in the target vehicle exceeding a threshold range, acquiring, by a controller, the second health state of the battery disposed in the target vehicle from a battery management system.

15. The method according to claim 13, wherein: Acquiring a second health status of a battery disposed in the target vehicle includes: determining, by a controller, the reliability of the first state of health of a battery provided in the target vehicle based on the extent to which the first state of health deviates from a threshold range; In response to the reliability not exceeding the threshold, a second health state of a battery provided in the target vehicle is acquired by the controller from the battery management system.

16. The method according to claim 15, wherein: Correcting the first health state further includes determining, by the controller, a reflection rate of the second health state based on the determined reliability.

17. A system for predicting the health status of a battery, the system comprising: A server configured to train a health status prediction model using a training data set, wherein the training data set includes battery information of a battery in a detection vehicle, driving information of the detection vehicle, and a health status of the battery in the detection vehicle; A health state prediction device includes a controller configured to predict a first health state of a battery provided in a target vehicle based on a health state prediction model, The controller of the health state prediction device is configured to predict the first health state by utilizing the speed and accumulated mileage of the target vehicle and at least one of the voltage, current, temperature and number of charging times of the battery in the target vehicle.

18. The system for predicting the health status of a battery according to claim 17, wherein: The battery information includes detecting at least one of a voltage, a current, a temperature, a number of fast charges, a number of slow charges, or a combination thereof in a battery of the vehicle.

19. The system for predicting the health status of a battery according to claim 17, wherein: The driving information includes at least one of the speed, accumulated mileage, and driving time of the detection vehicle, or a combination thereof.

20. The system for predicting the health status of a battery according to claim 17, wherein: The controller is further configured to acquire a second state of health of a battery provided in the target vehicle from a battery management system through a vehicle network, and correct the first state of health by using the second state of health.

Images