BATTERY DETERIORATION DETERMINATION DEVICE, BATTERY DETERIORATION DETERMINATION METHOD, AND BATTERY DETERIORATION DETERMINATION PROGRAM

• Main Author: HAGA NOBUYASU
• Format: Patent
• Language: English; Japanese
• Published: 30.08.2021
• Subjects: BASIC ELECTRIC ELEMENTS; CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTINGELECTRIC POWER; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER; ELECTRICITY; GENERATION; MEASURING; MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES; PERFORMING OPERATIONS; PHYSICS; PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSIONOF CHEMICAL INTO ELECTRICAL ENERGY; SYSTEMS FOR STORING ELECTRIC ENERGY; TESTING; TRANSPORTING; VEHICLES IN GENERAL; VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISEPROVIDED FOR

To provide a battery deterioration determination device, battery deterioration determination method, and battery deterioration determination program capable of highly accurately determining deterioration of a battery even in a case with insufficient data.SOLUTION: A center 12 includes: a data reception section 30 for receiving a state quantity of a battery 20 to be transmitted from an on-vehicle device 16; a probability calculation section 42 for calculating a deterioration probability in a short term, a deterioration probability in a middle term, and a deterioration probability in a long term by defining a state quantity of the battery 20 as an input with the use of a data map generated by machine learning by an AI model; and a deterioration determination section 44 for determining deterioration of the battery 20 based on a deterioration probability in a long term in an initial stage with less teacher data, and determining deterioration of the battery 20 based on a deterioration probability in a short term when teacher data is increased.SELECTED DRAWING: Figure 2 【課題】データが十分に揃ってない場合であってもバッテリの劣化を高精度に判定可能なバッテリ劣化判定装置、バッテリ劣化判定方法、及びバッテリ劣化判定プログラムを提供することを目的とする。【解決手段】センタ１２は、車載器１６から送信されるバッテリ２０の状態量を受信するデータ受信部３０と、ＡＩモデルによる機械学習により作成したデータマップを用いてバッテリ２０の状態量を入力として、短期での劣化確率、中期での劣化確率、及び長期での劣化確率を算出する確率算出部４２と、教師データが少ない初期の場合は、長期での劣化確率に基づいて、バッテリ２０の劣化を判定し、教師データが増えてくると、短期での劣化確率に基づいて、バッテリ２０の劣化を判定する劣化判定部４４と、を含む。【選択図】図２