메뉴 건너뛰기
소속 기관 / 학교 인증
인증하면 논문, 학술자료 등을  무료로 열람할 수 있어요.
한국대학교, 누리자동차, 시립도서관 등 나의 기관을 확인해보세요
(국내 대학 90% 이상 구독 중)
고객센터 ENG
주제분류

논문 기본 정보

저자정보
(한동대학교) (아이카) (한동대학교)
저널정보
한국자동차공학회 한국자동차공학회 추계학술대회 및 전시회 2025년 한국자동차공학회 추계학술대회 및 전시회
오류 신고하기

피인용 0

검색

    초록·키워드

    As efforts to mitigate climate change accelerate, the adoption of electric vehicles(EV) is rapidly expanding. However, the range estimates that vehicle dashboards provide are often inaccurate, which poses a major barrier to widespread EV adoption. This study proposes a robust range prediction framework that is based on large-scale real-world Battery Management System(BMS) data. Specifically, the study constructs a dataset that includes 11,512,182 km of driving records, which are collected over 25 months from 391 EVs. To overcome the practical limitation that complete discharge data are rarely available, we reformulate the range prediction task as an energy efficiency(km/kWh) prediction problem. A Transformer-based prediction model is designed, which captures complex correlations and long-term dependencies within multivariate time-series data. Experimental results show that the proposed Transformer model achieved a MAE(mean absolute error) of 5.38 km, reducing prediction error by approximately 49.2% compared to EV dashboards.

    최근 본 자료 전체보기

      UCI(KEPA) : I410-151-26-02-095660310