【作者】 赵立宏； 邓骞；

【Author】 ZHAO Li-hong,DENG Qian (School of electrical engineering,University of South China,Hengyang of Hunan Prov.421001,China)

【机构】 南华大学电气工程学院；

【摘要】 核设施结构复杂,所处高辐照环境下,人员难以靠近。针对这些情况,提出了对核设施运行时所产生的音频信号进行基于隐马尔可夫模型HMM(Hidden Markov Model)故障诊断的方法。HMM具有强大的建模能力,非常适用于分析诸如音频信号等非平稳时间信号。采用此方法可在不破坏核设施原有机械结构的基础上进行设备的故障诊断与实时监控,整个诊断系统所需的前置传感器单元数量少,结构简单,成本低廉,故障诊断率高。更多还原

【Abstract】 Due to the complex structure of nuclear facilities in a high irradiation environment,people are hard to approach it.In view of these situations,a fault diagnosis method based on HMM(Hidden Markov Model)of capturing the audio signal while the nuclear facilities are operating is proposed.With the strong modeling ability,HMM can be applied to analyzing such as audio signal non-stationary time signal.By using this method,the original mechanical structures of nuclear facilities are not destroyed.The preposed sensors are needed as few as possible by the whole diagnosis system and which has a simple structure,low cost structure.The fault diagnosis rate is high.更多还原