基于小波包和神经网络的瓦斯传感器故障诊断  

Gas sensor fault diagnosis based on wavelet packet and neural network

作　　者：赵金宪[1,2] 金鸿章[1] 

机构地区：[1]哈尔滨工程大学自动化学院,黑龙江哈尔滨150001 [2]黑龙江科技学院电气与信息工程学院,黑龙江哈尔滨150027

出　　处：《传感器与微系统》2010年第5期80-82,共3页Transducer and Microsystem Technologies

摘　　要：针对瓦斯传感器常见的故障,提出了基于小波包和神经网络的故障诊断方法。通过对瓦斯传感器的输出信号进行三层小波包分解,得到8个不同频段的分解信号,再对其进行特征提取得到一个八维的特征向量,作为故障样本对三层神经网络进行训练,建立故障类型分类器,对瓦斯传感器故障进行诊断。仿真结果表明:该方法可以准确地诊断出故障类型。Aimed at the common gas sensor fault, the approach of fault diagnosis based on wavelet packet and neural network is discussed. The output of gas sensor by three-layer wavelet packet is decomposed to achieve eight signals of different frequency bands. An 8-dimeusional eigenvector of vibrating signals was constructed for training 3-layer neural network. The fault type classifier is established for the gas sensor fault diagnosis. The simulation result shows that the proposed method can detect faults accurately.

关 键 词：小波包分解 神经网络 故障诊断 瓦斯传感器 

分 类 号：TP206[自动化与计算机技术—检测技术与自动化装置]