Vehicle battery diagnostic system

Abstract

A vehicle battery diagnosis system (1) diagnoses the remaining life of a battery (11) mounted in a vehicle (10). A vehicle battery diagnosis system (1) is provided with an information acquisition unit (101), a learning completion model acquisition unit (103), a remaining life diagnosis unit (105), and a diagnosis result output unit (106). An information acquisition unit (101) acquires at least vehicle information of a vehicle and use experience information of a battery (11). A learning completion model acquisition unit (103) acquires at least vehicle information of a vehicle (10) in which a battery (11) is mounted and use experience information of the battery (11) as explanatory variables, and a learning completion model created in advance with the remaining life of the battery (11) as a target variable. A remaining life diagnosis unit (105) diagnoses the remaining life of the battery (11) on the basis of the vehicle information acquired by the information acquisition unit (101), the use experience information, and the learning completion model. A diagnosis result output unit (106) outputs the diagnosis result of the remaining life diagnosis unit (105).

Description

[0001] Cross-reference to related applications

[0002] This application is based on Japanese application No. 2022-79294 filed on May 13, 2022, and the contents described therein are incorporated herein by reference. Technical Field

[0003] The invention relates to a battery diagnosis system for a vehicle. Background Art

[0004] In the past, as a structure for diagnosing and confirming the life of a battery installed in a vehicle, for example, Patent Document 1 discloses a structure that diagnoses the deterioration state of multiple battery cells constituting the battery installed in the vehicle, and displays the remaining life of the battery cells on multiple screens based on this, which can be confirmed separately by vehicle manufacturers, dealers, vehicle users, etc.

[0005] Prior art literature

[0006] Patent Literature

[0007] Patent Document 1: Japanese Patent Application Publication No. 2010-111276

[0008] In the structure disclosed in Patent Document 1, the battery voltage and impedance value of the battery cell are used to diagnose the degradation state in a short time, but the vehicle information including the region where the vehicle equipped with the battery is used and the driving distance of the vehicle is not considered. Therefore, the accuracy of the degradation information is low, and the diagnosis system of the remaining life is also reduced. Therefore, there is room for improvement in order to diagnose the remaining life with high accuracy. Summary of the invention

[0009] The present disclosure provides a vehicle battery diagnosis system capable of diagnosing the life of a battery mounted on a vehicle with high accuracy.

[0010] One aspect of the present disclosure is a vehicle battery diagnosis system for diagnosing the remaining life of a battery mounted on a vehicle, comprising:

[0011] an information acquisition unit, the information acquisition unit acquiring at least vehicle information of the vehicle and usage history information of the battery;

[0012] a learned model acquisition unit that acquires a learned model that is prepared in advance using at least vehicle information of the vehicle equipped with the battery and usage history information of the battery as explanatory variables and a remaining life of the battery as a target variable;

[0013] a remaining life diagnosing unit configured to diagnose the remaining life of the battery based on the vehicle information and the usage history information acquired by the information acquiring unit and the learned model; and

[0014] A diagnosis result output unit is configured to output a diagnosis result of the remaining life diagnosis unit.

[0015] In the vehicle battery diagnosis system, the remaining life of the battery mounted on the vehicle is diagnosed based on at least information about the vehicle on which the battery is mounted and information about the battery's usage history, and a pre-made battery model, thereby being able to diagnose the remaining life of the battery in a short time with high accuracy.

[0016] As described above, according to the above aspect, it is possible to provide a vehicle battery diagnosis system capable of diagnosing the remaining life of a battery mounted on a vehicle with high accuracy.

[0017] In addition, the symbols in the parentheses in the claims indicate the correspondence relationship between specific technical means described in the embodiments described later, and do not limit the technical scope of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The above-mentioned object and other objects, features and advantages of the present disclosure will become more apparent through the following detailed description with reference to the accompanying drawings.

[0019] Figure 1 is a block diagram showing the structure of a vehicle battery diagnosis system in Embodiment 1.

[0020] Figure 2 is a conceptual diagram showing a learning-completed model feature space in Implementation Example 1.

[0021] Figure 3 This is a conceptual diagram showing the relationship between battery recycling, reorganization order estimation, and inventory target in the first embodiment.

[0022] Figure 4 is a flowchart of the preliminary determination process in the first embodiment.

[0023] Figure 5 This is a flowchart of the post-processing of the preliminary determination in the first embodiment.

[0024] Figure 6 is a flowchart of the model update process in Implementation Method 1.

[0025] Figure 7 is a flowchart of the inventory update process in Implementation Method 1.

[0026] Figure 8is a flowchart of the remaining life diagnosis process and the reorganization process in the first embodiment.

[0027] Fig. 9 This is a flowchart of related processing in the first embodiment. DETAILED DESCRIPTION

[0028] (Implementation Method 1)

[0029] use Figures 1 to 9 An embodiment of the above-mentioned vehicle battery diagnosis system will be described.

[0030] The vehicle battery diagnosis system 1 of the first embodiment is used to diagnose the remaining life of a battery 11 mounted on a vehicle 10. Figure 1 As shown, the vehicle battery diagnosis system 1 includes an information acquisition unit 101 , a learned model acquisition unit 103 , a remaining life diagnosis unit 105 , and a diagnosis result output unit 106 .

[0031] The information acquisition unit 101 acquires at least vehicle information of the vehicle and usage history information of the battery 11 .

[0032] The learned model acquisition unit 103 acquires a learned model prepared in advance using at least vehicle information of the vehicle 10 equipped with the battery 11 and the usage history information of the battery 11 as explanatory variables and the remaining life of the battery 11 as a target variable.

[0033] The remaining life diagnosis unit 105 diagnoses the remaining life of the battery 11 based on the vehicle information and the usage history information acquired by the information acquisition unit 101 and the learned model.

[0034] The diagnosis result output unit 106 outputs the diagnosis result of the remaining lifetime diagnosis unit 105 .

[0035] Hereinafter, the vehicle battery diagnosis system 1 according to the present embodiment will be described in detail.

[0036] 1. Structure of vehicle battery diagnosis system 1

[0037] like Figure 1 As shown, in the first embodiment, the vehicle battery diagnosis system 1 is constructed by the components of the dealer 100, the server 200, and the centralized repair shop 300. Figure 1 The configurations of the dealer 100, the server 200, and the centralized repair shop 300 shown in the figure may be configurations of any one of the dealer 100, the server 200, and the centralized repair shop 300. Furthermore, all elements constituting the vehicle battery diagnosis system 1 are not limited to the dealer 100, the server 200, and the centralized repair shop 300, but may be provided on a terminal or a cloud connected via a communication mechanism.

[0038] Furthermore, a battery 11 as a diagnostic target of the vehicle battery diagnostic system 1 is mounted on a vehicle 10 owned by a user. The battery 11 is a secondary battery that can be charged and discharged, and includes a battery composed of a single battery element or a plurality of battery elements. Furthermore, a plurality of batteries 11 are electrically connected to each other to form a battery pack 12. Furthermore, each battery 11 constitutes a module that can be individually loaded and unloaded from the battery pack 12. In addition, the battery 11 is not limited to the type of secondary battery, and a battery suitable for the vehicle 10 can be used.

[0039] 1-1. About Dealer 100

[0040] like Figure 1 As shown, the dealer 100 includes an information acquisition unit 101, a diagnosis possibility determination unit 102, a learning completed model acquisition unit 103, a learning completed model extraction unit 104, a remaining life diagnosis unit 105, a diagnosis result output unit 106, an update necessity determination unit 107, a storage necessity determination unit 108, a related information acquisition unit 109, a battery issuing unit 110, a reassembly information request input unit 120, an information transmission unit 121, an information reception unit 122, an information presentation unit 123, a reassembly request acceptance and transmission unit 124, a reception unit 125, and an assembly unit 126. Among these, the battery issuing unit 110 can be configured by a not-shown issuing system, the information presentation unit 123 can be configured by a not-shown display device, and the other components can be configured by a not-shown calculation processing unit.

[0041] The information acquisition unit 101 acquires at least vehicle information of the vehicle 10 and usage history information of the battery 11. In the first embodiment, the information acquisition unit 101 further acquires battery characteristics of the battery 11. First, the vehicle information is information about the vehicle 10, and for example, the type of vehicle 10, the date of manufacture, the period of use, the travel distance, the area of ​​use, etc. of the vehicle 10 can be exemplified. In addition, the date of manufacture does not necessarily need to be determined, and it is also possible to determine it to the year or month. The vehicle information can be acquired from a storage device (not shown) provided in the vehicle 10.

[0042] Furthermore, the usage history information of the battery 11 may be the maximum value, minimum value, average value, cumulative value, etc. within a specified period such as the charging and discharging of the battery 11, the battery temperature, the battery voltage, the capacity, the SOC (State of charge), or the usage period of the device equipped with the battery 11. The specified period may be any period up to the present, or may be the entire period from the manufacture of the secondary battery to the present. The usage history information of the battery 11 may be obtained from the BMU (Battery Management Unite) possessed by the battery 11. Furthermore, the battery characteristics of the battery 11 are information such as the current battery temperature, battery voltage, capacity, SOC, internal impedance, etc. of the battery 11. These may also be obtained from the BMU possessed by the battery 11.

[0043] In addition, usually, the information acquisition unit 101 acquires the above information from the battery 11 in the state of being mounted on the vehicle 10 brought by the user to the dealer 100. Therefore, among the battery information acquired from the battery 11, the battery temperature or other battery information does not have the same value among the plurality of batteries 11 mounted on the vehicle 10, and usually includes battery information of different values ​​from each other.

[0044] Next, the diagnosis possibility determination unit 102 determines whether the remaining life of the battery 11 can be diagnosed based on the above information acquired by the information acquisition unit 101. For example, when the SOC, voltage, or remaining capacity of the battery 11 is below a specified value, or when the internal impedance, charge and discharge times, manufacturing date, usage period, and driving distance of the battery 11 are above a specified value, the diagnosis possibility determination unit 102 can determine that the battery 11 cannot be diagnosed.

[0045] Furthermore, the diagnosis possibility determination unit 102 may determine whether the diagnosis of the battery 11 can be performed based on whether the above information obtained by the information acquisition unit 101 is included in the validity range of the learning model pre-set in the learning model obtained by the learning model acquisition unit 103 described later. The validity range of the learning model can be set, for example, based on the training data of each learning model. For example, in the data group of the training data of each learning model, the range of the distance between the data of the respective data center is within the prescribed reference value as the validity range, and it can be determined that the diagnosis is possible when it is determined that any of the distances between the above information obtained by the information acquisition unit 101 and the data of the respective data centers in the training data of the plurality of learning models is within the prescribed reference value, and it can be determined that the diagnosis is not possible otherwise. In addition, the possibility of the diagnosis determined by the diagnosis possibility determination unit 102 can be performed after the learning model is extracted by the learning model extraction unit 104, or at the same time as the learning model is extracted by the learning model extraction unit 104.

[0046] The battery 11 determined as undiagnosable by the diagnosis determination unit 102 does not require the diagnosis described below and is clearly unusable, so the calculation load can be reduced by eliminating it before the diagnosis described below. The battery 11 determined as undiagnosable can be discarded or its parts can be recovered by disassembly or the like.

[0047] The learning completion model acquisition unit 103 acquires the learning completion model from the server 200 described later. The learning completion model uses the above-mentioned information acquired by the information acquisition unit 101 as an explanatory variable and the remaining life of the battery 11 as a target variable. The learning completion model can be prepared by preparing teacher data and made through machine learning. In addition, the learning completion model can be updated as described later by using the vehicle battery diagnostic system 1 of this embodiment 1. Moreover, the learning completion model acquisition unit 103 can acquire the latest updated learning completion model. In addition, a plurality of learning completion models can be prepared as described later. In this embodiment 1, the learning completion model acquisition unit 103 acquires a plurality of learning completion models.

[0048] The learning model extraction unit 104 extracts the most appropriate learning model from the multiple learning models acquired by the learning model acquisition unit 103. The extraction can be performed based on the information acquired by the information acquisition unit 101. For example, when the battery temperature is lower than a predetermined reference value in the information acquired by the information acquisition unit 101, the learning model corresponding to it can be extracted. Moreover, for example, when the average value of the battery temperature experience is lower than the predetermined reference value or the frequency of the battery temperature experience at low temperatures is high, it can be expected that the battery 11 is used in a cold area, and the learning model corresponding to this can be extracted by the learning model acquisition unit 103. Moreover, in the information acquired by the information acquisition unit 101, when the battery 11 is a specific vehicle model, the learning model corresponding to the specific vehicle model can be extracted. Moreover, the learning model can be extracted based on the distance between the data of each data center in the data group of the training data of each learning model and the information acquired by the information acquisition unit 101.

[0049] The remaining life diagnosis unit 105 diagnoses the remaining life of the battery 11 determined as being diagnosable by the diagnosis feasibility determination unit 102, based on the above information acquired by the information acquisition unit 101 and the learning completion model. In the present first embodiment, the most appropriate learning completion model extracted by the learning completion model extraction unit 104 is used as the learning completion model. As a result, the remaining life can be diagnosed with higher accuracy. The diagnosis result of the remaining life diagnosis unit 105 is stored in the information accumulation unit 201 of the server 200 described later. In addition, the information is stored in the information accumulation unit 201 for each diagnosed battery 11, and the above information acquired by the information acquisition unit 101 can also be stored in the battery 11 together with the diagnosis result of the remaining life.

[0050] The diagnosis result output unit 106 outputs the diagnosis result of the remaining life diagnosis unit 105. The output format is not limited, and it can be displayed on the display unit, printed in writing, or notified by sound. In addition, the output content may also include matters accompanying the remaining life. In addition, the output content may be different for users and for dealers. For example, detailed information accompanying the remaining life of the battery 11 may be displayed in the content for dealers, while only whether the battery 11 needs to be replaced may be displayed in the content for users.

[0051] The update necessity determination unit 107 determines whether the learning completion model of the battery 11 stored in the server 200 described later must be updated. The determination criteria in the update necessity determination unit 107 are not limited, but in the first embodiment, when any one of the following four criteria is satisfied, it is determined that the above-mentioned update must be performed.

[0052] The first update criterion is whether the information acquired by the information acquisition unit 101 in the battery 11 is information belonging to an unlearned area in the latest learned model stored in the learned model storage unit 203 of the server 200. Figure 2 In the feature space defined by the feature quantity A and feature quantity B in the training data in the learning completed model shown, it is determined whether the unlearned area L1 is an unknown range outside the learning area Lt which is a known range in the training data. Here, the learning area Lt is a range within a predetermined distance from the center position Ct in the data space of the training data used in the latest learning completed model, and the range outside of it is regarded as the unlearned area L1. The distance between data can be defined based on Mahalanobis distance, Euclidean distance, Manhattan distance, Chebyshev distance, etc.

[0053] The second update criterion is whether the information belongs to the learning area Lt in the learning completed model, and the distance between the data center calculated based on the information within a specified period from the latest model update and the data center calculated based on all the information in the learning area Lt is greater than the reference value. Figure 2 As shown, it is determined whether the data distance D between the data center C2 in the data space of the data range L2 of the most recently added N=100 training data in the latest learned model and the data center C of all training data in the latest learned model is greater than the reference value.

[0054] The third update criterion is whether the information belongs to the learning area Lt in the learning completed model, and whether the difference between the data deviation calculated based on the information within a specified period from the latest model update and the data deviation calculated based on all the information in the learning area Lt is greater than the reference value. For example, Figure 2 As shown, it is determined whether the difference between the data deviation in the data space of the data range L3 of the most recently added N=100 training data in the latest learning completed model and the data deviation calculated based on the full information in the learning area Lt is greater than the reference value. The data deviation can be calculated, for example, based on the degree of deformation of the shape of the data range within the reference value of the data distance D from the data center C of the full training data in the relevant data space.

[0055] The fourth update criterion is whether the information belongs to the learning area Lt in the learning completed model, and whether the difference between the data density calculated based on the information within a specified period from the latest model update and the data density calculated based on the entire information in the learning area Lt is greater than the reference value. For example, Figure 2 As shown, it is determined whether the difference between the data density in the data space of the data range L4a, L4b of the N=100 training data most recently added in the latest learning completed model and the data density calculated based on the full information in the learning area Lt is greater than the reference value. The data density can be calculated, for example, as the number of data per unit area in the target data range in the data space.

[0056] The update necessity determination unit 107 determines that the learning completed model must be updated when the information acquired by the information acquisition unit 101 meets any of the first to fourth update criteria described above.

[0057] The storage necessity determination unit 108 determines whether the battery 11 must be stored in the centralized repair shop 300 described later for reassembly. In addition, reassembly refers to packaging a used battery pack in order to reuse it as a second-hand battery pack. For example, in the centralized repair shop 300, the used battery pack is disassembled into module units or battery element units, stored in a storage warehouse in layers according to the levels assigned based on the degree of deterioration, etc., and the modules or battery elements corresponding to the necessary levels are extracted from the storage warehouse again, reassembled and packaged, thereby reassembling. In addition, the used battery pack does not necessarily need to be disassembled / layered, and the substrate, wiring, or frame can be removed to form a battery pack set as an assembly of battery elements or modules, and the battery pack set can be directly used for new packaging, thereby reassembling.

[0058] The storage standard for reorganization, which is a determination standard in the storage necessity determination unit 108, is defined based on the inventory target received from the server 200 described later. Figure 3 In the example shown in (a), the relationship between the number of recovered batteries 11 and the value of the battery 11, such as the capacity, is displayed as for the recovered battery B. Furthermore, the relationship between the number of batteries estimated to be necessary for reorganization within a predetermined period in the future and the value level can be expressed in the reorganization order estimation Rb1. The inventory target Rb2 is set to a numerical value with a certain degree of margin corresponding to the reorganization order estimation Rb1. Furthermore, in the relationship between the inventory target Rb2 and the recovered battery B, whether it belongs to the area B1 surrounded by the inventory target Rb2, the recovered battery B and the horizontal axis becomes the storage criterion for reorganization in the storage necessity determination unit 108.

[0059] According to the storage criteria for reassembly, the batteries 11 belonging to the area B1 are determined to be necessary to be stored for reassembly, and the batteries 11 not belonging to the area B1 are determined to be unnecessary to be stored. Figure 3 In (a), among the recycled batteries B, the batteries 11 belonging to the area B2 on the upper side of the paper than the inventory target Rb2 are judged to be unnecessary to be kept for reorganization because they may become surplus inventory. In addition, when there are multiple uses for the battery 11, the reorganization order estimation Rb1 may also have a shape with multiple peaks in the graph representing the relationship between the value level and the number of batteries. For example, Figure 3 As shown in the example of (b), the reorganization order estimation Rb1 has two peaks, and correspondingly, the inventory target Rb2 also has two peaks. In this case, the storage standard for reorganization is also the same as Figure 3 The case of (a) is similarly defined based on the inventory target Rb2.

[0060] As described later, in the first embodiment, the batteries stored in the battery storage unit 306 of the centralized repair shop 300 are assigned grades according to the diagnosis results of the batteries 11, and the inventory information includes the number of batteries for each grade. Accordingly, the storage standard for reassembly also defines the number of batteries for each grade. In other words, the storage standard for reassembly is defined based on the inventory status in the battery storage unit 306 and the diagnosis results of the batteries 11.

[0061] The associated information acquisition unit 109 compares the battery information acquired by the information acquisition unit 101 from the battery 11 mounted on the vehicle with the battery information acquired from the battery 11 removed from the vehicle, and after confirming that both are battery information acquired from the same battery 11, acquires associated information as information associating them with the battery identification information of the battery 11. The form of the battery identification information is not limited, and can be a number, a mark, a one-dimensional barcode, a two-dimensional barcode, or a combination of these.

[0062] The battery information in the related information may be, for example, the battery voltage of the battery 11. The related information acquisition unit 109 may acquire the related information at a time immediately after being removed from the vehicle 10, or may acquire the related information at a time when a predetermined period has passed since being removed from the vehicle 10. When acquiring the related information at a time after the predetermined period has passed, the battery information in the related information may be corrected in consideration of a change in the battery information due to the passage of time, and the related information may be acquired using the corrected data.

[0063] The battery delivery unit 110 delivers the battery 11 to the centralized repair shop 300 described later. The delivered battery 11 is a battery determined by the update necessity determination unit 107 to require an update of the learning completed model, and a battery determined by the storage necessity determination unit 108 to require storage for reassembly.

[0064] Next, the reassembly information request input unit 120 allows the user to input information related to the reassembly of the battery pack 12 of the vehicle 10 after the user confirms the output result of the diagnosis result output unit 106, such as whether the battery 11 needs to be replaced. When the reassembly information request is input, the input result is sent to the centralized repair shop 300 described later through the information sending unit 121. In addition, the reassembly information sent from the centralized repair shop 300 is received by the information receiving unit 122, and the received content is prompted to the user through the information prompting unit 123. The prompting of this information can be performed by displaying it on a display unit not shown, printing it in writing, or notifying it with sound. In addition, the reassembly information includes information such as the delivery period or cost when reassembly is performed. Moreover, on this basis, the delivery period or cost of the parts necessary for replacing the battery 11 can also be included.

[0065] When the user confirms the reassembly information and requests to reassemble the battery pack, the reassembly request receiving and transmitting unit 124 receives the reassembly request and transmits the request to the centralized repair shop 300. The receiving unit 125 receives the reassembled battery pack sent from the centralized repair shop 300, and the assembling unit 126 assembles the reassembled battery pack into the user's battery pack 12. Then, the battery pack 12 is mounted on the vehicle 10. Furthermore, when the user wishes to replace the battery pack with a new one instead of the reassembled one, the reassembly request receiving and transmitting unit 124 can receive the request and place an order for the new one through the new product ordering unit 127.

[0066] 1-2. About Server 200

[0067] like Figure 1 As shown, the server 200 is connected to the dealer 100 and the centralized repair shop 300 described later via a network line. The server 200 can be set up in the cloud via an Internet line. The server 200 includes an information accumulation unit 201, a model update unit 202, a learning model storage unit 203, an inventory information acquisition unit 204, and an inventory target creation unit 205. These structures can be formed by a calculation processing device not shown.

[0068] The information integrating unit 201 integrates the information acquired by the information acquiring unit 101 of the dealer 100 and the diagnosis result of the remaining life diagnosing unit 105 with the diagnosis result of the battery diagnosing unit 305 in the centralized repair shop 300 described later.

[0069] The model updating unit 202 updates the learning completion model based on the information of the information accumulation unit 201. The updated learning completion model is stored in the learning completion model storage unit 203. The learning completion model can be a model made by machine learning using the information acquired by the information acquisition unit 101 as an explanatory variable and the remaining life as a target variable. The learning completion model can use a prediction model such as a regression equation, for example, linear regression, LASSO regression, Ridge regression, decision tree, support variable regression, etc. In addition, a neural network or XGBoost (eXtreme Gradient Boosting (Ensemble Learning) / Gradient Boosting Regression Tree) can also be constructed.

[0070] The inventory information acquisition unit 204 acquires inventory information of the batteries 11 stored as reassembled batteries 11 in the battery storage unit 306 in the centralized repair shop 300 described later. In addition, the inventory target creation unit 205 creates an inventory target based on the reassembled order forecast within a predetermined period. The inventory target can be, for example, Figure 3 The example shown is made as shown.

[0071] 1-3. About the 300 centralized repair shops

[0072] The centralized repair shop 300 performs repairs upon request from a plurality of dealers 100. The centralized repair shop 300 includes an information receiving unit 301, a reassembly information generating unit 302, an information transmitting unit 303, a receiving unit 304, a battery diagnosis unit 305, a battery storage unit 306, a reassembly unit 307, and a reassembled battery sending unit 308. Among these, the information receiving unit 301, the reassembly information generating unit 302, the information transmitting unit 303, the receiving unit 304, and the battery diagnosis unit 305 can be configured by a calculation processing device (not shown).

[0073] The information receiving unit 301 receives the input information of the reorganization request sent from the information sending unit 121 of the dealer 100. The reorganization information generating unit 302 generates the reorganization information including the delivery date and cost of the reorganized battery based on the input information of the reorganization request. The generated reorganization information is sent to the dealer 100 via the information sending unit 303 and received by the information receiving unit 122.

[0074] The receiving unit 304 receives the battery 11 sent by the battery sending unit 110 of the dealer 100. The received battery 11 is diagnosed by the battery diagnosis unit 305. The diagnosis performed by the battery diagnosis unit 305 is a more detailed diagnosis than the diagnosis by the remaining life diagnosis unit 105 of the dealer 100, and has more diagnostic items. In addition, in order to improve the accuracy of the diagnosis, the diagnosis can also be performed after the temperature of the battery 11 is brought to a predetermined state. For this reason, it takes more time to obtain the diagnosis result than the diagnosis by the remaining life diagnosis unit 105 of the dealer 100. The diagnostic method in the battery diagnosis unit 305 is not limited as long as it is a method that can perform a detailed diagnosis. For example, for the battery 11, the battery characteristics related to the changes in the battery state throughout the predetermined voltage range can be obtained, and the degree of deterioration can be determined based on the battery characteristics or the battery characteristic relationship value calculated based on the battery characteristics, and the value of the battery 11 is evaluated and rated.

[0075] The battery storage unit 306 is composed of a warehouse capable of storing the batteries 11. The storage status of the batteries 11 in the battery storage unit 306, that is, the inventory information including the number of stored batteries 11 and battery information of these batteries 11, is sent to the server 200 and acquired by the inventory information acquisition unit 204. In the present first embodiment, the batteries are stored in the battery storage unit 306 in a state where they are ranked according to the diagnosis results of the battery diagnosis unit 305. In addition, the above inventory information also includes information on the number of batteries for each rank.

[0076] The reassembly unit 307 receives a reassembly request from the reassembly request receiving and transmitting unit 124 of the dealer 100 and reassembles the battery corresponding to the request. The reassembled battery is then shipped to the dealer 100 by the reassembled battery shipping unit 308 and received by the receiving unit 125.

[0077] 2. Control flow of vehicle battery diagnosis system 1

[0078] 2-1. Preliminary judgment and processing

[0079] Next, regarding the control flow of the vehicle battery diagnosis system 1, first, Figure 4 In the prior determination process, Figure 4 In step S1 shown, the information acquisition unit 101 of the dealer 100 acquires the voltage as vehicle information of the vehicle 10, the usage history information of the battery 11, and the battery characteristics of the battery 11. The acquired information is stored in the information accumulation unit 201 of the server 200.

[0080] Then, in step S2, it is determined by the update necessity determination unit 107 whether the information acquired by the information acquisition unit 101 satisfies the first update criterion. If it is determined that the acquired information satisfies the first update criterion, that is, if it is determined that the acquired information is information belonging to the unlearned area L1 in the latest learned model stored in the learned model storage unit 203 of the server 200, the process proceeds to step S2, and in step S3, it is determined that the associated processing is to be performed and the preliminary determination processing is terminated.

[0081] On the other hand, in step S2, if the update necessity determination unit 107 of the dealer 100 determines that the information acquired by the information acquisition unit 101 does not satisfy the first update criterion, the process proceeds to step S2 with a "No", and in step S4, it is determined whether the information acquired by the information acquisition unit 101 satisfies any one of the second to fourth update criteria. If it is determined that the acquired information satisfies any one of the second to fourth update criteria, the process proceeds to step S4 with a "Yes", and in step S3, it is determined that the associated processing is to be performed, and the preliminary determination processing is terminated.

[0082] Furthermore, in step S4, if it is determined that the acquired information does not satisfy any of the second to fourth update criteria, the process proceeds to step S4 with a "No". Furthermore, in step S5, it is determined whether the storage necessity determination unit 108 of the dealer 100 satisfies the storage criteria for reorganization. If it is determined that the storage criteria for reorganization are satisfied, the process proceeds to step S5 with a "Yes", and in step S3, it is determined that the associated process is to be performed, and the preliminary determination process is terminated.

[0083] On the other hand, if it is determined in step S5 that the storage standard for reassembly is not satisfied, the process proceeds to No in step S5, and in step S6 it is determined that the waste is to be disposed of or collected, and the preliminary determination process ends.

[0084] 2-2. Pre-judgment and post-processing

[0085] Next, the post-pre-determination processing in the control flow of the vehicle battery diagnosis system 1 will be described. Figure 5 As shown, the pre-judgment post-processing performs parallel processing of steps S7 to S8, step S9, and step S10. In step S7, which is the first parallel processing, the battery 11 determined to be subjected to the associated processing in the above step S3 is removed from the vehicle and the associated processing described later is performed. Then, in step S8, it is sent to the centralized repair shop 300. In step S9, which is the second parallel processing, the battery 11 determined to be recycled in the above step S6 is removed from the vehicle by disassembly, etc., and the parts are taken out, and the parts are recycled for reuse. Moreover, in step S10, which is the third parallel processing, the battery 11 determined to be discarded in the above step S6 is removed from the vehicle and discarded.

[0086] 2-3. Model update processing

[0087] Next, the model update process in the control flow of the vehicle battery diagnosis system 1 will be described. Figure 6 As shown, in the model update process, first, in step S11, the centralized repair shop 300 receives a battery 11 that satisfies any one of the first to fourth update criteria from the dealer 100. Then, in step S12, the battery diagnosis unit 305 of the centralized repair shop 300 performs a detailed diagnosis of the battery 11. The diagnosis result of the detailed diagnosis is stored in the information accumulation unit 201 of the server 200. In the first embodiment, the degree of deterioration of the battery 11 is calculated and the remaining life is diagnosed as the diagnosis result. Then, in step S13, the learning completion model is updated by the model update unit 202 based on the diagnosis result, and the model update process ends.

[0088] 2-4. Inventory update processing

[0089] Next, the inventory update process in the control flow of the vehicle battery diagnosis system 1 will be described. Figure 7 As shown, in the model update process, first, in step S15, the centralized repair shop 300 receives the battery 11 that meets the storage standard for reassembly from the dealer 100. Then, in step S16, the battery 11 is stored in the battery storage unit 306 of the centralized repair shop 300 as inventory for reassembly. Furthermore, in step S17, the inventory information acquisition unit 204 of the server 200 acquires inventory information from the battery storage unit 306 and updates the inventory information. Based on the inventory information, the inventory target creation unit 205 creates an inventory target and updates the above-mentioned storage standard for reassembly, and the inventory update process ends.

[0090] In addition, for the Figure 6The battery 11 sent to the centralized repair shop 300 by the model update process shown can also be determined whether it meets the Figure 4 The storage standard for reassembly in step S5 shown in FIG. 1 is applicable to batteries that meet the storage standard for reassembly. Figure 7 The stock update process shown is performed, and the battery is stored in the battery storage unit 306 for reorganization stock as necessary.

[0091] Furthermore, in step S15, the remaining life diagnostic unit 105 may perform detailed diagnosis on the battery 11 that meets the storage criteria for rebuilding and is sent to the centralized repair shop 300, and store the battery 11 in the battery storage unit 306 in a graded state based on the detailed diagnosis result.

[0092] 2-5. Remaining life diagnosis and reorganization

[0093] Next, the remaining life diagnosis process and the reassembly process in the control flow of the vehicle battery diagnosis system 1 will be described. Figure 4 In step S1 shown in FIG. 1 , the information acquisition unit 101 of the dealer 100 acquires the vehicle information of the vehicle 10, the usage history information of the battery 11, and the battery characteristics of the battery 11, and then sends the vehicle information to the dealer 101 as shown by symbol A. Figure 8 The process proceeds to step S20.

[0094] Then, in step S20, the diagnosis availability determination unit 102 determines whether the battery 11 can be diagnosed based on the information acquired by the information acquisition unit 101. If it is determined that the battery 11 cannot be diagnosed, the process proceeds to No in step S20 and the process ends.

[0095] On the other hand, in step S20 , when it is determined that the battery 11 can be diagnosed, the process proceeds to YES in step S20 . Then, in step S21 , the learned model extraction unit 104 extracts the most appropriate learned model.

[0096] Then, in step S22, the remaining life diagnosis unit 105 of the dealer 100 diagnoses the remaining life of the battery 11 when the battery 11 is mounted on the vehicle based on the information acquired by the information acquisition unit 101 and the most appropriate learned model. In step S23, the diagnosis result output unit 106 outputs the diagnosis result to a display unit (not shown) and transmits it to the information accumulation unit 201 of the server 200.

[0097] Then, in step S24, the reassembly information request input unit 120 of the dealer 100 determines whether there is a request for reassembly information, which is a material for determining whether the user places an order for a reassembled product. If there is a request for reassembly information, the process proceeds to step S24, and in step S25, the reassembly information is prepared by the reassembly information preparation unit 302 of the centralized repair shop 300, and the reassembly information is sent to the dealer 100 from the information transmission unit 303. In addition, the reassembly information also includes information on the delivery date or cost when a new battery is used instead of a reassembled product. Then, the reassembly information is received by the information receiving unit 122 of the dealer 100, and the reassembly information is presented to the user by the information presentation unit 123. The user can determine whether to perform reassembly by considering the delivery date or cost of the reassembled battery included in the reassembly information.

[0098] Furthermore, in step S26, the reassembly request receiving and transmitting unit 124 of the dealer 100 determines whether the user has input a reassembly request as an intention to reassemble. If the user has input a reassembly request, the process proceeds to step S26 and transmits the reassembly request to the centralized repair shop 300. If the reassembly request is received by the reassembly unit 307 of the centralized repair shop 300, in step S27, the centralized repair shop 300 extracts a battery corresponding to the reassembly request from a plurality of batteries stored in the battery storage unit 306, and manufactures a reassembled battery on the basis of the battery. Alternatively, a plurality of batteries determined to be stored in the battery storage unit 306 may be combined to manufacture a plurality of reassembled batteries of various grades in advance, and the batteries may be stored in the battery storage unit 306, and batteries that meet the reassembly request may be extracted from the stored reassembled batteries. Then, in step S28, the manufactured or extracted reassembled batteries are shipped from the centralized repair shop 300 to the dealer 100 by the reassembled battery shipping unit 308.

[0099] Then, after the dealer 100 receives the reassembled battery through the receiving unit 125, in step S29, the assembly unit 126 of the dealer 100 forms the battery pack 12 using the reassembled battery and assembles it into the vehicle 10. This process flow ends.

[0100] On the other hand, in step S26, if there is no input of a reassembly request from the user, the process proceeds to step S26 No, and in step S30, it is determined whether the user wishes to replace the battery with a new one in the reassembly request receiving and sending unit 124. If the user wishes to replace the battery with a new one, the process proceeds to step S30 Yes, and in step S31, an order for a new battery is placed with a battery manufacturer (not shown) through the new product ordering unit 127 of the dealer 100. When the new battery arrives at the dealer 100, it is received by the receiving unit 125, and the battery pack 12 is formed using the new battery by the assembling unit 126 and assembled in the vehicle 10. Thus, this processing flow ends. Furthermore, in step S30, if the user does not wish to replace the battery with a new one, the process proceeds to step S30 No, and in step S32, it is determined that the battery 11 is not to be replaced, and this processing flow ends.

[0101] Furthermore, in step S24, if the user has not made a request for reorganization information, the process proceeds to No in step S24, and in step S2, it is determined that the battery 11 is not to be replaced, and this processing flow ends.

[0102] In the first embodiment, the battery stored in the battery storage unit 306 is used in response to the reassembly request from the user, but it can also be replaced by replacing a part of the battery 11 originally mounted on the user's vehicle 10 and sent to the centralized repair shop 300, and then returning it to the user as a reassembled product.

[0103] 2-6. Related Processing

[0104] Then Figure 4 The associated processing in step S7 shown is Fig. 9 First, Figure 8 In step S22 shown in FIG. 1 , the remaining life diagnostic unit 105 of the dealer 100 diagnoses the remaining life of the battery 11 in the state where the battery 11 is mounted on the vehicle, and after the diagnosis result is stored in the information accumulation unit 201 of the server 200, as shown by symbol B, the remaining life diagnostic unit 105 of the dealer 100 diagnoses the remaining life of the battery 11 in the state where the battery 11 is mounted on the vehicle, and the diagnosis result is stored in the information accumulation unit 201 of the server 200. Fig. 9 Then, the process proceeds to step S40 . Then, in step S40 , the related information acquiring unit 109 of the dealer 100 acquires the battery identification information of the battery 11 removed from the vehicle 10 .

[0105] Furthermore, in step S41, the battery voltage of the removed battery 11 is directly measured and obtained as a direct battery characteristic. Then, in step S42, since the change in the battery voltage as a direct battery characteristic is taken into account with the time elapsed from the removal of the battery 11 from the vehicle 10 to the measurement of the battery voltage, the battery voltage as a direct battery characteristic is corrected according to the time elapsed. In addition, when the time elapsed is shorter than a predetermined reference value, the change in the battery voltage accompanying the time elapsed may be ignored, and step S42 may not be performed.

[0106] Then, in step S43, the battery voltage before removal and after removal or correction is compared to determine whether the two are consistent. If it is determined that the two are consistent, the process proceeds to step S43, and in step S44, the information obtained from the vehicle 10 before removal is associated with the information of the battery 11 after removal, and the process ends.

[0107] On the other hand, in step S43, if it is determined that the battery voltages before removal and after removal or after correction are inconsistent, the information obtained from the vehicle 10 before removal is inconsistent with the information of the battery 11 after removal, and the two are not related, and the process returns to step S41, and the battery voltage after removal is obtained again, and the battery voltage after removal is corrected in step S42. In addition, in step S43, the battery voltage after correction after removal is compared with the battery voltage before removal in another battery 11 different from the battery compared last time, and it is determined whether the two are consistent. Based on the comparison result, step S44 is performed as described above, or the steps since step S41 are performed again.

[0108] In the present embodiment, the correlation process in step S7 is performed in the dealer 100 , but the present invention is not limited thereto and may be performed in the centralized repair shop 300 after the battery 11 is shipped from the dealer 100 to the centralized repair shop 300 .

[0109] Next, the effects of the vehicle battery diagnosis system 1 of the first embodiment are described in detail. In the vehicle battery diagnosis system 1 of the first embodiment, the remaining life of the battery 11 mounted on the vehicle 10 is diagnosed based on at least the information of the vehicle 10 equipped with the battery 11 and the battery usage history information, and the pre-made learning model. As a result, the remaining life of the battery 11 can be diagnosed in a short time with high accuracy.

[0110] Furthermore, in the first embodiment, the battery 11 is provided with a diagnosis possibility determination unit 102 for determining whether or not the remaining life can be diagnosed, and the remaining life diagnosis unit 105 diagnoses the remaining life of the battery 11 determined as being diagnosable by the diagnosis possibility determination unit 102. Thus, the remaining life of the battery 11 does not need to be diagnosed for an excessively deteriorated battery or a damaged battery, and the efficiency of the calculation process can be improved.

[0111] Moreover, in the first embodiment, the learned model acquisition unit 103 acquires a plurality of learned models prepared in advance. Furthermore, a learned model extraction unit 104 is provided, which extracts at least one from the plurality of learned models acquired by the learned model acquisition unit 103 based on the information acquired by the information acquisition unit 101. Furthermore, the remaining life diagnosis unit 105 uses the learned model extracted by the learned model extraction unit 104 as the learned model. Thus, the remaining life diagnosis unit 105 can diagnose the remaining life based on the most suitable learned model corresponding to the information acquired by the information acquisition unit 101, so that the diagnosis accuracy can be improved.

[0112] Furthermore, in the first embodiment, the model updating unit 202 is provided for updating the learned model based on the information acquired by the information acquiring unit 101. Thus, even if the degradation tendency of the battery 11 changes, the learned model can be updated accordingly, so that the remaining life can be diagnosed more accurately.

[0113] Furthermore, in the first embodiment, an update necessity determination unit 107 is provided for determining whether or not the learned model of the battery 11 must be updated. This allows detailed diagnosis to be performed only on the battery 11 that must be updated, and the efficiency of the calculation process can be improved.

[0114] Furthermore, in the first embodiment, when the information acquired by the information acquisition unit satisfies at least one of the following conditions: the information belongs to the unlearned area in the learned model; the information belongs to the learned area in the learned model, and the data distance between the data center calculated from the information within a predetermined period from the latest model update and the data center calculated from the entire information in the learned area is greater than the reference value; the information belongs to the learned area in the learned model, and the difference between the data deviation calculated from the information within a predetermined period from the latest model update and the data deviation calculated from the entire information in the learned area is greater than the reference value; and the information belongs to the learned area in the learned model, and the difference between the data density calculated from the information within a predetermined period from the latest model update and the data density calculated from the entire information in the learned area is greater than the reference value, the update necessity determination unit 107 determines that the learned model must be updated. Thus, the battery 11 required for updating the learned model can be optimally extracted, and the diagnosis of the remaining life can be further improved in accuracy.

[0115] Furthermore, in the first embodiment, there is provided a storage necessity determination unit 108 for determining whether or not the battery 11 should be stored in the reassembly stock of the battery 11. This can prevent the batteries stored for reassembly from being left over.

[0116] Furthermore, in the first embodiment, the storage necessity determination unit 108 determines whether or not the battery 11 must be reassembled based on the inventory target calculated corresponding to the inventory information of the battery stored as the reassembly inventory. Thus, it is possible to efficiently acquire and store batteries having battery characteristics that are insufficient in the reassembly inventory, and it is possible to suppress the burden of excess inventory and optimize inventory management.

[0117] Furthermore, in the first embodiment, the batteries stored in the battery storage unit 306 of the centralized repair shop 300 are ranked according to the diagnosis results of the batteries 11, and the inventory information includes the number of batteries for each rank. Furthermore, the storage standard for rebuilding, which is a standard for determining whether to store the batteries in the rebuilding inventory, also specifies the number of batteries for each rank. In other words, the storage standard for rebuilding is specified based on the inventory status in the battery storage unit 306 and the diagnosis results of the batteries 11. As a result, the inventory management of the batteries can be performed in consideration of the rank of the batteries 11, and the inventory management can be further optimized.

[0118] Furthermore, in the first embodiment, the information acquisition unit 101 also acquires the battery characteristics of the battery 11 as the above-mentioned information. This allows the remaining life to be diagnosed in consideration of the battery characteristics, and thus the accuracy of the diagnosis can be further improved.

[0119] Furthermore, in the first embodiment, there is further provided an associated information acquisition unit 109, which compares the battery characteristics acquired by the information acquisition unit 101 from the battery 11 mounted on the vehicle 10 with the direct battery characteristics acquired by directly measuring the battery 11 after the battery 11 is removed from the vehicle 10, and associates the information acquired by the information acquisition unit 101 with the battery identification information of the battery 11. Thus, it is possible to ensure that the information acquired in the state where it is difficult to physically identify the battery 11 mounted on the vehicle 10 is the information of the battery 11, and it is possible to prevent the wrong battery from being taken, thereby improving the reliability of the diagnosis result.

[0120] Furthermore, in the first embodiment, the associated information acquisition unit 109 corrects the battery characteristics obtained by directly measuring the battery 11 according to the time from when the battery 11 was removed from the vehicle 10 to when the battery 11 was directly measured, and uses the corrected battery characteristics as the direct battery characteristics. Thus, even when using the battery characteristics obtained after a time has passed since the battery 11 was removed from the vehicle 10, the accuracy of the association can be improved, and the reliability of the diagnosis result can be improved by preventing the wrong battery from being taken.

[0121] As described above, according to the first embodiment, it is possible to provide the vehicle battery diagnosis system 1 capable of diagnosing the remaining life of the battery 11 mounted on the vehicle 10 with high accuracy.

[0122] The present disclosure is not limited to the above-described embodiments, but can be applied to various embodiments without departing from the gist of the present disclosure.

[0123] The features of the present disclosure are as follows.

[0124] [Project 1]

[0125] A vehicle battery diagnostic system (1) for diagnosing the remaining life of a battery mounted on a vehicle (10), comprising:

[0126] An information acquisition unit (101) that acquires at least vehicle information of the vehicle and usage history information of the battery;

[0127] a learning-completed model acquisition unit (103) which acquires a learning-completed model prepared in advance by using at least vehicle information of the vehicle equipped with the battery and usage history information of the battery as explanatory variables and the remaining life of the battery as a target variable;

[0128] a remaining life diagnosing unit (105) for diagnosing the remaining life of the battery based on the vehicle information and the usage history information acquired by the information acquiring unit and the learning completion model; and

[0129] A diagnosis result output unit (106) outputs the diagnosis result of the remaining life diagnosis unit.

[0130] [Project 2]

[0131] The vehicle battery diagnostic system as described in item 1 above, wherein:

[0132] A diagnosis possibility determination unit (102) is provided, which determines whether or not the remaining life of the battery can be diagnosed.

[0133] The remaining life diagnosing unit diagnoses the remaining life of the battery determined as diagnosable by the diagnosis possibility determining unit.

[0134] [Item 3]

[0135] A vehicle battery diagnostic system as described in item 1 or 2 above, wherein:

[0136] The learned model acquisition unit acquires a plurality of the learned models prepared in advance.

[0137] A learning completion model extraction unit (104) is provided, which extracts at least one of the multiple learning completion models obtained by the learning completion model acquisition unit based on the information obtained by the information acquisition unit, and the remaining life diagnosis unit uses the learning completion model extracted by the learning completion model extraction unit as the learning completion model.

[0138] [Item 4]

[0139] The vehicle battery diagnostic system according to any one of items 1 to 3 above, wherein:

[0140] A model updating unit (202) is provided, which updates the learned model based on the information acquired by the information acquiring unit.

[0141] [Item 5]

[0142] The vehicle battery diagnostic system as described in item 4 above, wherein:

[0143] An update necessity determination unit (107) is provided for determining whether or not the learning completed model of the battery must be updated.

[0144] [Item 6]

[0145] The vehicle battery diagnostic system as described in item 5 above, wherein:

[0146] When the information obtained by the above information acquisition unit meets the following requirements:

[0147] When the information belongs to the unlearned area in the above-mentioned learning completion model;

[0148] The information belongs to the learning area in the above-mentioned learning completed model, and the distance between the data of the data center calculated based on the information within a specified period from the latest model update and the data of the data center calculated based on all the information in the above-mentioned learning area is greater than the reference value;

[0149] The information belongs to the learning area in the above-mentioned learning completed model, and the difference between the data deviation calculated based on the information within a specified period from the latest model update and the data deviation calculated based on all the information in the above-mentioned learning area is greater than the reference value; and

[0150] is information belonging to the learning area in the above-mentioned learning completed model, and the difference between the data density calculated based on the information within a specified period from the latest model update and the data density calculated based on the entire information in the above-mentioned learning area is greater than the reference value,

[0151] When at least one of the above is satisfied, the update necessity determination unit determines that the learning completion model must be updated.

[0152] [Item 7]

[0153] The vehicle battery diagnosis system according to any one of items 1 to 6 above, wherein:

[0154] A storage necessity determination unit (108) is provided, which determines whether the battery should be stored in a battery reassembly inventory.

[0155] [Item 8]

[0156] The vehicle battery diagnostic system as described in item 7 above, wherein:

[0157] The storage necessity determination unit determines whether the batteries must be reassembled based on a stock target calculated in accordance with stock information of the batteries stored as the reassembly stock.

[0158] [Item 9]

[0159] The vehicle battery diagnostic system according to any one of items 1 to 8 above, wherein:

[0160] The information acquisition unit further acquires battery characteristics of the battery.

[0161] [Item 10]

[0162] The vehicle battery diagnostic system as described in item 9 above, wherein:

[0163] It also has an associated information acquisition unit (109), which compares the battery characteristics obtained by the information acquisition unit from the battery in the state of being mounted on the vehicle with the direct battery characteristics obtained by directly measuring the battery after removing it from the vehicle, and associates the information obtained by the information acquisition unit with the battery identification information of the battery.

[0164] [Item 11]

[0165] The vehicle battery diagnostic system according to item 10 above, wherein:

[0166] The battery characteristics acquired by directly measuring the battery are corrected according to a time lapse from when the battery is removed from the vehicle to when the battery is directly measured, and the related information acquisition unit uses the corrected battery characteristics as the direct battery characteristics.

[0167] The present disclosure is carried out according to the embodiment, but it should be understood that the present disclosure is not limited to the embodiment or structure. The present disclosure includes various deformation modes or deformations within the scope of equality. In addition, various combinations or methods, and then, other combinations or methods containing only one element, above or below them also fall into the category or scope of thought of the present disclosure.

Claims

1. A vehicle battery diagnostic system (1), for diagnosing the remaining life of a battery mounted on a vehicle (10), characterized in that: have: An information acquisition unit (101) which acquires at least vehicle information of the vehicle and usage history information of the battery; a learning-completed model acquisition unit (103) which acquires a learning-completed model prepared in advance by using at least vehicle information of the vehicle equipped with the battery and usage history information of the battery as explanatory variables and the remaining life of the battery as a target variable; a remaining life diagnosing unit (105) for diagnosing the remaining life of the battery based on the vehicle information and the usage history information acquired by the information acquiring unit and the learning completion model; and A diagnosis result output unit (106) outputs the diagnosis result of the remaining life diagnosis unit.

2. The vehicle battery diagnostic system according to claim 1, wherein: A diagnosis possibility determination unit (102) is provided, the diagnosis possibility determination unit determining whether or not the remaining life of the battery can be diagnosed. The remaining life diagnosing unit diagnoses the remaining life of the battery determined as diagnosable by the diagnosis possibility determining unit.

3. The vehicle battery diagnostic system according to claim 1 or 2, characterized in that: The learned model acquisition unit acquires a plurality of the learned models prepared in advance, The vehicle battery diagnosis system comprises a learned model extraction unit (104) which extracts at least one of the plurality of learned models acquired by the learned model acquisition unit based on the information acquired by the information acquisition unit. The remaining life diagnosis section uses the learned model extracted by the learned model extraction section as the learned model.

4. The vehicle battery diagnostic system according to claim 1 or 2, characterized in that: A model updating unit (202) is provided, which updates the learned model based on the information acquired by the information acquiring unit.

5. The vehicle battery diagnostic system according to claim 4, characterized in that: An update necessity determination unit (107) is provided for determining whether or not the battery needs to update the learned model.

6. The vehicle battery diagnostic system according to claim 5, characterized in that: When the information acquired by the information acquisition unit satisfies: When the information belongs to an unlearned area in the learning completed model; The information belongs to the learning area in the learned model, and the distance between the data of the data center calculated based on the information within a predetermined period from the latest model update and the data of the data center calculated based on all the information in the learning area is greater than the reference value; The information belongs to the learning area in the learned model, and the difference between the data deviation calculated based on the information within a specified period from the latest model update and the data deviation calculated based on all the information in the learning area is greater than the reference value; and is information belonging to the learning area in the learning completed model, and the difference between the data density calculated based on the information within a specified period from the latest model update and the data density calculated based on all the information in the learning area is greater than the reference value, When at least one of the following is true, the update necessity determination unit determines that the learning completed model must be updated.

7. The vehicle battery diagnostic system according to claim 1 or 2, characterized in that: A storage necessity determination unit (108) is provided, which determines whether the battery should be stored in a battery reassembly inventory.

8. The vehicle battery diagnostic system according to claim 7, wherein: The storage necessity determination unit determines whether the battery must be reassembled based on a stock target calculated in accordance with stock information of the battery stored as the reassembly stock.

9. The vehicle battery diagnostic system according to claim 1 or 2, characterized in that: The information acquisition unit further acquires battery characteristics of the battery.

10. The vehicle battery diagnostic system according to claim 9, characterized in that: It also has an associated information acquisition unit (109) that compares the battery characteristics acquired by the information acquisition unit from the battery mounted on the vehicle with direct battery characteristics acquired by directly measuring the battery after it is removed from the vehicle, and associates the information acquired by the information acquisition unit with the battery identification information of the battery.

11. The vehicle battery diagnostic system according to claim 10, wherein: The battery characteristics acquired by directly measuring the battery are corrected according to a time lapse from when the battery is removed from the vehicle to when the battery is directly measured, and the related information acquisition unit uses the corrected battery characteristics as the direct battery characteristics.

Images