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
- 학위논문
- 저자정보
- 지도교수
- 朴商皓
- 발행연도
- 2013
- 저작권
- 충남대학교 논문은 저작권에 의해 보호받습니다.
이용수2
이 논문의 연구 히스토리 (2)
- 이 논문의 후속연구가 궁금하신가요?
- 연관 학술논문 또는 학술발표를 통해 보다 발전된 연구결과를 확인하실 수 있습니다.
- 이 논문의 연구 히스토리 확인하기
초록· 키워드
오류제보하기
Automobile (Ship) the electronic engine control system are consists of the various sensors that operating state of the engine into electrical signals sent to the computer to change and ECU that Signal analysis, determine the fuel injector valve opening or the time to determine the amount.
However, these sensors using the information in order to control the introduction of electronic control systems, strong fault diagnosis technique fault conditions of should be developed for can have a significant impact on performance.
Fault diagnosis determines the malfunction in a system and classifies the failures. The conventional fault diagnosis method can be classified as a model based method and non-model based method.
In this paper is proposed, the relationship between the sensor signal and the engine output by calculating the correlation between the selection of the sensor and the high of this sensor model based on the sensor signal fault diagnosis algorithm.
Among the model-based fault diagnosis methods the parameter estimation method has been used to estimate the parameters. Based on the estimated parameters an algorithm has been proposed to diagnose the fault.
In addition, based on the estimated parameters the residuals were generated. The waveform analyzes of residuals were performed in real time and created a data. The data collected was then compared with the database for fault diagnostics.
The residuals waveforms were classified based on type to determine the failure. These waveforms were used in the hidden Markov model algorithms.
In addition, For order to verify the algorithm finally saw simulate using real data collected real sensor and developed fault diagnostic program using C & Android
However, these sensors using the information in order to control the introduction of electronic control systems, strong fault diagnosis technique fault conditions of should be developed for can have a significant impact on performance.
Fault diagnosis determines the malfunction in a system and classifies the failures. The conventional fault diagnosis method can be classified as a model based method and non-model based method.
In this paper is proposed, the relationship between the sensor signal and the engine output by calculating the correlation between the selection of the sensor and the high of this sensor model based on the sensor signal fault diagnosis algorithm.
Among the model-based fault diagnosis methods the parameter estimation method has been used to estimate the parameters. Based on the estimated parameters an algorithm has been proposed to diagnose the fault.
In addition, based on the estimated parameters the residuals were generated. The waveform analyzes of residuals were performed in real time and created a data. The data collected was then compared with the database for fault diagnostics.
The residuals waveforms were classified based on type to determine the failure. These waveforms were used in the hidden Markov model algorithms.
In addition, For order to verify the algorithm finally saw simulate using real data collected real sensor and developed fault diagnostic program using C & Android
목차
Ⅰ. 서론 11.1 연구 필요성 11.2 연구 동향 21.2 연구 방법 3Ⅱ. 고장 진단 이론 62.1 고장 진단 배경 62.2 고장 진단 종류 7Ⅲ. Raw Data 가공 93.1 Raw Data 93.2 Raw Data Filtering 103.3 상관 관계 13Ⅳ. 고장 진단 194.1 Modified Kalman Filter 194.2 계수 추정 및 잔차 생성 214.3 Hidden Markov Model 284.4 HMM을 이용한 잔차 파형 분류 31Ⅴ. 안드로이드 어플리케이션 개발 35Ⅵ. 결론 40
최근 본 자료
댓글(0)
0