基于小波包的2D-HMM旋转机械升速过程故障诊断  

Fault Diagnosis in Speed-up Process of a Rotating Machine Based on Wavelet Packet and 2DHMM

作　　者：叶大鹏[1] 丁启全[1] 吴昭同[1] 

机构地区：[1]浙江大学机械与能源工程学院

出　　处：《农业机械学报》2004年第1期117-120,共4页Transactions of the Chinese Society for Agricultural Machinery

基　　金：国家自然科学基金资助项目 (项目编号 :5 0 0 75 0 79)

摘　　要：利用小波包分解对信号进行精确细分的特点 ,构造出相应的能量谱作为旋转机械运行状态的特征向量 ,并以此作为 2 D HMM的输入进行训练 ,建立了基于 2 D HMM的旋转机械运行状态分类器 ,用以识别机组状态。最后通过 Bently-The energy spectrum from the wavelet packet decomposition can be used as feature vectors of running state of a rotating machine to train 2DHMM. So the classified model based on 2DHMM was constructed. The new model was tested with the experimental data collected from a BentlyNevada rotor experimental system and the result demonstrated that the model was effective to classify classical faults in speed up process of a rotating machine.

关 键 词：小波包分解 2D—HMM旋转机械 升速过程 故障诊断 能量谱 二维隐马尔可夫模型 

分 类 号：TH17[机械工程—机械制造及自动化]