지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
논문 기본 정보
- 자료유형
- 학술저널
- 저자정보
- 발행연도
- 2018.12
- 수록면
- 281 - 290 (10page)
- DOI
- 10.33162/JAR.2018.12.18.4.281
이용수
이 논문의 연구 히스토리 (3)
- 이 논문의 후속연구가 궁금하신가요?
- 연관 학술논문 또는 학술발표를 통해 보다 발전된 연구결과를 확인하실 수 있습니다.
- 이 논문의 연구 히스토리 확인하기
초록· 키워드
오류제보하기
Purpose: Recently vehicle sensor data can be collected in real time based by Electronic Control Unit (ECU) such as engine, transmission, chassis, tire, and battery modules etcs. The purpose of this study is related to simply find the Pre-Ignition occurrence patterns without labeled training data set using unsupervised learning approach. Because there are many unknown problem cases even engineer could not be recognized in the vehicle development period.
Methods: Applied the advanced analytical techniques such as deep learning, feature extraction, clustering. We have compared many algorithms to optimize detecting problem area. Convolutional Neural Network AutoEncoder, Self Organized Map, Multi Dimensional Scaling (MDS) used in this study.
Results: Implementation of various pre-ignition related pattern detecting methodology and detection model using State-of-Art Deep Learning algorithm.
Conclusion: We have developed an algorithm to detect the pre-ignition pattern which is related to a fatal problem for engine side. Deep Learning Analytic model such as Combining AutoEncoder and Self-Organizing Map (SOM) can be used automatically finding hidden problem areas among the vehicle generated sensor signal. This approach is a proven methodology and can be used to analyze various sensor signal problems during vehicle development phase in the future.
Methods: Applied the advanced analytical techniques such as deep learning, feature extraction, clustering. We have compared many algorithms to optimize detecting problem area. Convolutional Neural Network AutoEncoder, Self Organized Map, Multi Dimensional Scaling (MDS) used in this study.
Results: Implementation of various pre-ignition related pattern detecting methodology and detection model using State-of-Art Deep Learning algorithm.
Conclusion: We have developed an algorithm to detect the pre-ignition pattern which is related to a fatal problem for engine side. Deep Learning Analytic model such as Combining AutoEncoder and Self-Organizing Map (SOM) can be used automatically finding hidden problem areas among the vehicle generated sensor signal. This approach is a proven methodology and can be used to analyze various sensor signal problems during vehicle development phase in the future.
목차
1. 서론
2. 본론
3. 결론
References
참고문헌 (9)
참고문헌 신청
[학술지(정기간행물)] - Kim, M. H. / 2013 / Study about detection & prohibition of irregular combustion investigation in gasoline turbo GDI engine / KSAE 2013 (11) : 161 ~ 167
[학술지(정기간행물)] - Lee, H. S. / 2014 / The effects of fuel composition on pre-ignition in gasoline turbo-charged engine / KSAE 2014 (5) : 18 ~ 25
[학술지(정기간행물)] - Kim, T. M. / 2016 / Characteristics of pre-ignition on different lubricant and fuel in turbo-charged direct injection spark ignition engines / Korea Automotive Engineering Committee 2016 (11) : 38 ~
[학술지(정기간행물)] - Lim, G. H. / 2017 / Study on major factors for protecting low speed pre-Ignition (LSPI) in turbocharged gasoline direct injection engine / Korea Automotive Engineering Committee 2017 (11) : 176 ~ 181
[학술대회논문] - Im, H. G. / 2015 / An ignition regime diagram and its implications in pre-ignition and super-knock for IC engine application / KOSCO Symposium 51 : 25 ~ 39
[학술지(정기간행물)] - Lee, H. S. / 2014 / The effects of fuel composition on pre-ignition in gasoline turbo-charged engine / KSAE 2014 (5) : 18 ~ 25
[학술지(정기간행물)] - Kim, T. M. / 2016 / Characteristics of pre-ignition on different lubricant and fuel in turbo-charged direct injection spark ignition engines / Korea Automotive Engineering Committee 2016 (11) : 38 ~
[학술지(정기간행물)] - Lim, G. H. / 2017 / Study on major factors for protecting low speed pre-Ignition (LSPI) in turbocharged gasoline direct injection engine / Korea Automotive Engineering Committee 2017 (11) : 176 ~ 181
[학술대회논문] - Im, H. G. / 2015 / An ignition regime diagram and its implications in pre-ignition and super-knock for IC engine application / KOSCO Symposium 51 : 25 ~ 39
함께 읽어보면 좋을 논문
논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!
-
딥러닝을 활용한 엔진오일 타입에 따른 엔진 조기점화 특성에 대한 연구
한국트라이볼로지학회 학술대회
2019 .04
-
An Ignition Regime Diagram and Its Implications in Pre-ignition and Super-knock for IC Engine Applications
KOSCO SYMPOSIUM 논문집
2015 .12
-
면적비 변화에 따른 튜브 내 고압 수소 자발점화현상 연구
KOSCO SYMPOSIUM 논문집
2015 .12
-
점화원 위치 및 점화시간 변화에 따른 백드래프트 거동에 관한 수치적 연구
한국안전학회지
2016 .01
-
Recommendation system using Deep Autoencoder for Tensor data
한국컴퓨터정보학회논문지
2019 .08
-
비지도 딥러닝 및 자기조직 신경망을 이용한 영상 분류 알고리즘 개발
제어로봇시스템학회 국내학술대회 논문집
2018 .05
-
다단연소사이클 엔진 재점화 시스템 구성 및 단독시험
한국추진공학회 학술대회논문집
2021 .05
-
딥러닝을 이용한 시계열데이터 군집화
신뢰성응용연구
2019 .06
-
A Study on the Flash Point and Spontaneous Ignition Determination of Diethylene Glycol
한국태양에너지학회 학술대회논문집
2015 .10
-
A Study on the Flash Point and Spontaneous Ignition Determination of Diethylene Glycol
한국태양에너지학회 논문집
2016 .04
-
Suggestion for deep learning approach to solve the interference effect of ammonium ion on potassium ion-selective electrode
한국표면공학회지
2022 .06
-
주변 센서 정보를 이용한 자동차 엔진 이상 탐지
한국소음진동공학회논문집
2022 .10
-
액체 로켓엔진에서 레이저 점화 기술 적용 검토
한국추진공학회지
2025 .02
-
Development of a Deep Learning Based 4D-Radar and Low-Cost Vision Sensor Fusion Algorithm for Vehicle Detection
한국자동차공학회 춘계학술대회
2022 .06
-
액체로켓 발사체의 재점화 엔진 시동 고찰
한국추진공학회 학술대회논문집
2021 .11
-
0-D 모델을 통한 CI 엔진에서의 점화지연 예측
한국자동차공학회 춘계학술대회
2019 .05
-
A study on ignition delay of compression ignition engine with a rapid compression expansion machine
한국자동차공학회 춘계학술대회
2017 .05
-
Experimental Investigation of Ignition and Combustion Dynamics of Ethane-Oxygen Mixtures Using Spark Ignition Systems
대한기계학회 춘추학술대회
2024 .11
-
모델 섹터 연소기의 점화기 깊이에 따른 점화특성 연구
한국연소학회지
2017 .06
-
Comparison of Deep Learning Algorithms Based on Face Recognition
ITC-CSCC :International Technical Conference on Circuits Systems, Computers and Communications
2015 .06
이 논문의 저자 정보
이 논문과 함께 이용한 논문
드론 개발 동향 및 관련 기술 소개
조창환
,
박성준
,
엄인섭
외 1명
정보과학회지
2019
.01
다목적 뇌-컴퓨터 인터페이스 게임
정성준
,
김준호
,
엄수상
외 3명
한국정보과학회 학술발표논문집
2018
.06
인공신경망과 유전알고리즘 기반의 쌍대반응표면분석에 관한 연구
T
,
itiya R. A
,
ungpadang
외 1명
대한산업공학회지
2013
.10
무조건 딥러닝?
이종석
ie 매거진
2019
.03
Generation of contrast enhanced computed tomography image using deep learning network
Sang-Keun Woo
한국컴퓨터정보학회논문지
2019
.03
최근 본 자료
댓글(0)
0