摘要
正确识别机械设备从正常到故障之间的演化过程,对掌握设备运行状态和预防故障发生具有重要意义。本文以柴油发电机组的气门漏气状态研究为例,建立了基于变尺度特征提取与隐式半马尔科夫模型(HSMM)的状态识别方法。变尺度小波包特征提取方法能有针对性地提取蕴含更多状态信息的振动信号特征,隐式半马尔科夫模型是一个强大的状态识别与故障预测工具,二者的有效结合能在较大程度上提高设备状态识别准确率。
It is significant to identify the evolvement from normal to fault for acquainting the running -states and avoiding the fault. In the paper, the Hidden Semi-Markov model （HSMM） based on the character picking-up with varying scales is built with the example of valve leaking on diesel dynamotor. The signal characters with more state information can be obtained pertinently by using the character picking-up with varying scales. The HSMM is a powerful state identification and fault prediction tool. The veracity of state identification can be improved effectively by banding them together.
出处
《小型内燃机与摩托车》
CAS
北大核心
2009年第6期80-82,共3页
Small Internal Combustion Engine and Motorcycle
基金
江西省自然科学基金项目(2008GQC0002)
江西省教育厅科技资助项目(GJJ08448)
关键词
柴油发电机组
状态识别
变尺度特征提取
隐式半马尔科夫模型
Diesel dynamotor, State identification, Character picking-up with varying scales, Hidden semi - Markov models
