摘要
旋转机械升速过程具有信息量大、信号非平稳、重复再现性不佳等特点 ,二维隐 Markov模型 ( 2 D-HMM)很适合处理此类信号。将 2 D-HMM引入到旋转机械升速过程的故障诊断中 ,提出了一种基于 2 D-HMM的故障诊断方法 ,描述了该模型的拓扑结构和主要参数以及相应的训练和识别算法。最后通过
There is a large amount non-stationary, worse reappearance signal in the rotor run-up process. 2DHMM is suitable to deal with these signals. So a new fault diagnosis strategy based on 2-dimensional hidden Markov was produced in this paper. The topology of this model and its parameters were introduced too. Finally, the new model was tested with experimental data collected from Bently-Nevada rotor experimental system (Model 24755) and the results demonstrate that it is very effective to diagnose the rotor faults.
出处
《中国机械工程》
EI
CAS
CSCD
北大核心
2003年第13期1149-1151,共3页
China Mechanical Engineering
基金
国家自然科学基金资助项目(50 0 750 79)
关键词
旋转机械
故障诊断
二维隐Markov模型
状态监测
rotating machinery fault diagnosis 2DHMM(2D hidden Markov Model) condition monitoring
