CN-122017638-A - Battery degradation degree prediction system

Abstract

The present invention relates to a battery degradation degree prediction system. The battery degradation degree prediction system includes a database for storing degradation degrees of secondary batteries for driving each of a plurality of vehicles, and a data set selection unit for changing a data set used for learning a model for predicting future degradation degrees of the secondary batteries of each of the plurality of vehicles, according to a storage state of the database.

Inventors

• Hizawa Yingming
• INOUE MASAAKI
• Fukuzumi Shintaro
• MASANORI OKAMOTO

Assignees

• 丰田自动车株式会社

Dates

Publication Date

20260512

Application Date

20250725

Priority Date

20241112

Claims (4)

1. 1. A battery degradation degree prediction system is provided with: A database for storing the degradation degree of the secondary battery for driving respectively mounted on a plurality of vehicles, and And a data set selection unit that changes a data set used for learning a model for predicting a future degradation degree of each of the secondary batteries of the plurality of vehicles, according to a storage state of the database.
2. 2. The battery degradation prediction system according to claim 1, wherein, The data set selection unit selects, as a data set used in learning of a model that predicts a degree of deterioration in the future of the secondary battery of one of the plurality of vehicles stored in the database, a data set containing a plurality of degrees of deterioration of the secondary battery of the one vehicle, according to a storage condition of the database.
3. 3. The battery degradation prediction system according to claim 1, wherein, The data set selection unit selects, as a data set used in learning of a model for predicting a future degradation degree of a secondary battery of one of the plurality of vehicles stored in the database and a plurality of degradation degrees of a secondary battery of a vehicle of the same type as the one vehicle, based on a storage condition of the database.
4. 4. The battery degradation prediction system according to claim 1, wherein, The data set selection unit selects, as a data set used in learning a model for predicting a future degradation degree of a secondary battery of the one vehicle, a data set including a secondary battery of the one vehicle and a plurality of degradation degrees of secondary batteries of the same type as the secondary battery of the one vehicle, which are stored in the database, according to a storage condition of the database.

Description

Battery degradation degree prediction system Technical Field The present invention relates to the field of battery degradation degree prediction systems for predicting degradation degree of secondary batteries. Background As such a system, for example, a system is proposed in which a prediction model is learned, and an index relating to the degradation state of the battery is estimated based on the learned prediction model (see japanese patent application laid-open No. 2023-51009), and the prediction model estimates an index relating to the degradation state of the battery based on learning data. Disclosure of Invention In the technique described in japanese patent application laid-open No. 2023-51009, an index relating to the degradation state of the battery is estimated based on a prediction model learned by machine learning. However, the estimation accuracy may be low based on learning data used for machine learning. The present invention has been made in view of the above-described problems, and an object thereof is to provide a battery degradation degree prediction system capable of improving estimation accuracy. A battery degradation degree prediction system according to an aspect of the present invention includes a database storing degradation degrees of secondary batteries for driving each of a plurality of vehicles, and a data set selection unit that changes a data set used for learning a model for predicting future degradation degrees of the secondary batteries of each of the plurality of vehicles, based on a storage state of the database. Drawings Features, advantages, and technical and industrial significance of exemplary embodiments of the present invention will be described below with reference to the accompanying drawings, in which like reference numerals denote like elements, and in which: Fig. 1 is a schematic diagram showing the structure of a battery degradation degree prediction system according to an embodiment; fig. 2 is a flowchart showing the operation of the battery degradation degree prediction system according to the embodiment; FIG. 3 is a flow chart showing a method of determining data for use in learning, and Fig. 4 is a flowchart showing a model construction method. Detailed Description An embodiment of a battery degradation degree prediction system will be described with reference to fig. 1 to 4. In fig. 1, a battery degradation degree prediction system 10 includes a database 11, a data set selection unit 12, and a model learning unit 13. For example, the battery degradation degree prediction system 10 may be implemented by a server. The battery degradation degree prediction system 10 may be implemented by a single server or by a plurality of servers. The server may be a cloud server. The battery degradation degree prediction system 10 is configured to be capable of two-way communication with a plurality of vehicles V1, V2. The plurality of vehicles V1, V2,..vn are mounted with secondary batteries B1, B2,..bn for driving, respectively. The plurality of vehicles V1, V2, vn may include at least one of a battery electric vehicle (battery ELECTRIC VEHICLE), a plug-in hybrid ELECTRIC VEHICLE, a hybrid electric vehicle (hybrid ELECTRIC VEHICLE), and a fuel cell electric vehicle (fuel CELL ELECTRIC VEHICLE). The secondary batteries B1, B2, bn may comprise at least one of lithium ion batteries, nickel hydrogen batteries, and all-solid-state batteries. Each of the plurality of vehicles V1, V2, vn periodically transmits data including the degree of degradation (State of Health): SOH) of the secondary battery to the battery degradation degree prediction system 10. The data may include specification information, a time stamp, characteristics related to the vehicle and the battery, and information related to the degree of degradation. For example, the specification information includes a vehicle identification number (Vehicle Identification Number:vin), a battery number, a battery model number, a vehicle model number, a destination, and a design change version. The information ON the degree of degradation may include the degree of degradation, the number of days elapsed since L/O (Line Off) (i.e., production completion date), the travel distance, the cumulative parking time, the SOC (State of Charge) history and battery temperature history in ignition ON, the SOC history and battery temperature history in ignition Off, and the like. The ignition ON may include at least one of running of the vehicle, power transmission mode use, and charging. The ignition OFF may include at least one of parking and transportation. The plurality of data transmitted from the plurality of vehicles V1, V2, vn, respectively, are stored in the database 11. As a result, the degradation degrees of the secondary batteries B1, B2, & gt, bn are stored in the database 11. The battery degradation degree prediction system 10 performs learning of a model for predicting the future degradation degree of the secondary batte