은닉 마르코프 모델; 결함 진단; 특징 벡터; 벡터 양자화; 질량 편심; 회전기기; Hidden Markov Model; Fault Diagnosis; Feature Vector; Vector Quantization; Mass Unbalance; Rotating Machine; HMM
Issue Date
2015-04
Publisher
한국소음진동공학회
Citation
춘계학술대회 논문집, 2015.4, 830-831 (2 pages)
Abstract
In recent years, pattern recognition methods have been widely used by many researchers for fault diagnoses of mechanical systems. A pattern recognition method determines the soundness of a mechanical system by detecting variations in the system's vibration characteristics. Hidden Markov model has recently been used as pattern recognition methods in various fields. In this paper, a hidden markov model method for the fault diagnosis of a rotating system is introduced, and a rotating machine with mass unbalance and bearing fault is selected for fault diagnosis. Moreover, a diagnosis procedure to identity the size of a defect is proposed in this paper.