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
(Handong Global University) (AiCAR) (Handong Global University)
저널정보
한국자동차공학회 한국자동차공학회 추계학술대회 및 전시회 2024년 한국자동차공학회 추계학술대회 및 전시회
오류 신고하기

피인용 0

검색

    초록·키워드

    This study presents a predictive approach to evaluating the energy efficiency of electric vehicle (EV) batteries using Phraformer, a Transformer-based architecture enhanced with a Pyramidal Attention Module (PAM). Energy efficiency, defined as the distance traveled per unit of State of Charge (SOC), is crucial metric for assessing battery performance and addressing range anxiety. The model processes real-world BMS data from 205 EVs across multiple scales and captures both short-term and long-term trends. To enhance prediction accuracy, we apply sequence-to-sequence (seq2seq) modeling to incorporate information from multiple prevoius time steps. The Pyraformer demonstrates improves performance over traditional models such as Long Short-Term Memory (LSTM) and Transformer models by achieving a Symmetric Mean Absolute Percentage Error (SMAPE) of 6.488% and Root Mean Squared Error (RMSE) of 0.466. The model effectively handles data variability and noise utilizing multi-scale attention and results in more accurate energy efficiency predictions. These results highlight the potential of Pyraformer for real-world applications in energy management and battery health monitoring, and alleviating range anxiety for EV users.

    최근 본 자료 전체보기