The present invention relates to a system and method for predicting a battery remaining lifespan based on incremental machine learning. The method for predicting the battery remaining lifespan based on incremental machine learning according to the present invention comprises: a step of predicting, by a remaining lifespan prediction part, a battery remaining lifespan (RUL) value by receiving learning data of a driving pattern similar to a driving pattern of a monitored user from an external server; a step of calculating, by a driving habit analysis part, an average value of the battery RUL value predicted by the remaining lifespan prediction part and the battery RUL value extracted from a server, and updating a weight and bias of an incremental machine learning model of a machine learning model part by labeling the average value thereof as an observation value of the collected user driving pattern data; and a step of displaying, by an instrument display part, the remaining life of the battery predicted by the remaining life prediction part and the driving habit of a driver analyzed by the driving habit analysis part on a display screen.

    본 발명은 점진적 머신 러닝 기반의 배터리 잔존 수명 예측 시스템 및 방법에 관한 것이다. 본 발명에 따른 점진적 머신 러닝 기반의 배터리 잔존 수명 예측 방법은, 머신 러닝 모델부가 임의의 전기자동차 배터리의 데이터를 입력받아 사용자의 운전 패턴을 모니터링하는 단계; 잔존수명 예측부가 모니터링된 사용자의 운전 패턴과 유사한 운전 패턴의 학습 데이터를 외부의 서버에서 받아와 배터리 잔존수명(RUL) 값을 예측하는 단계; 주행습관 분석부가 잔존수명 예측부에 의해 예측된 배터리 RUL 값과 서버에서 추출된 배터리 RUL 값의 평균값을 구하고, 그 평균값을 수집된 사용자의 운전 패턴 데이터의 관측값으로 라벨링하여 머신 러닝 모델부의 점진적 머신 러닝 모델의 가중치와 편향치를 업데이트하는 단계; 및 계기 표시부가 잔존수명 예측부에 의해 예측된 배터리의 잔존수명 및 주행습관 분석부에 의해 분석된 운전자의 주행습관을 디스플레이 화면에 표시하는 단계를 포함한다.


    Access

    Download


    Export, share and cite



    Title :

    Battery Remaining Useful Life Prediction System and Method based on Incremental Machine Learning


    Additional title:

    점진적 머신 러닝 기반의 배터리 잔존 수명 예측 시스템 및 방법


    Contributors:

    Publication date :

    2024-03-21


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Korean


    Classification :

    IPC:    B60L PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES , Antrieb von elektrisch angetriebenen Fahrzeugen / B60W CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION , Gemeinsame Steuerung oder Regelung von Fahrzeug-Unteraggregaten verschiedenen Typs oder verschiedener Funktion / G01R Messen elektrischer Größen , MEASURING ELECTRIC VARIABLES / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen




    Prediction of Mining Railcar Remaining Useful Life

    Rahimdel, Mohammad Javad / Ghodrati, Behzad / Vahed, Amir Taghizadeh | Springer Verlag | 2019


    Prediction of Remaining Useful Life for Aero-Engines

    B, Rounak / J, Manikandan | IEEE | 2021


    Prediction of Lithium-ion Battery's Remaining Useful Life Based on Relevance Vector Machine

    Huang, Miaohua / Zhu, Shuanglong / Chen, Yupu et al. | SAE Technical Papers | 2016


    Similarity-based remaining useful life prediction method under varying operational conditions

    Li, Qi / Gao, Zhanbao / Li, Shanying et al. | British Library Online Contents | 2016