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
(충남대학교) (충남대학교)
저널정보
대한전자공학회 대한전자공학회 학술대회 2025년도 대한전자공학회 하계학술대회 논문집
오류 신고하기

피인용 0

검색

    초록·키워드

    This study explores the predictability of fault code occurrences using vehicle driving data collected via On-Board Diagnostics II (OBDII). The analysis draws on both normal driving data and data from periods immediately preceding fault events. Traditional diagnostic systems are limited to post-fault responses. This study addresses that limitation by proposing a proactive approach. We applied the Cumulative Sum Control Chart (CUSUM) algorithm, a statistical method optimized to detect weak, gradually accumulating precursor signals of faults. During preprocessing, first-and second-order differencing were applied to improve time series stationarity and enhance sensitivity to subtle changes. CUSUM-based changepoint detection revealed significant anomalies in sensors such as RPM, particularly within data collected immediately before fault occurrences. These results confirm CUSUM’s effectiveness in capturing precursor signals prior to fault manifestation. This study demonstrates the feasibility of a lightweight diagnostic framework for proactive fault prediction, marking a shift from reactive post-fault responses to preventive maintenance.

    최근 본 자료 전체보기

      UCI(KEPA) : I410-151-25-02-093750923