Abstract: This paper presents an approach of feature extraction based on wavelet packet and kernel fisher and fuzzy pattern recognition for sensor fault diagnosis. Taking time domain features and frequency domain features of the sensor signal as initial features, valid features are extracted according to kernel fisher transform of initial feature vector, enhancing the signal characteristic. The sensor fault diagnosis model is established through use of fuzzy mathematics, the sensor state would be determined by getting membership degree of the feature vector for each state by membership function and using the principle of maximum membership to classify for the feature vector. The approach is applied to the FDT/DTM device management system, which is used for pressure sensor fault diagnosis in the water cycle control system of NCS4000, a numerical experiment shows that the algorithm is effective.

Key words: Kernel fisher, fuzzy pattern recognition, sensor fault diagnosis, Field Device Tool/Device Type Manager（FDT/DTM）

摘要： 提出了一种核Fisher特征提取以及模糊模式识别的传感器故障诊断方法。提取传感器信号波形时域特征和频域特征构成初始特征，使用核Fisher方法对初始特征进行非线性变换增强信号特征。然后使用模糊数学方法建立了传感器故障诊断模型，通过使用隶属度函数获取特征向量对各状态的隶属度，运用最大隶属原则对特征向量进行定性分类，判定传感器状态。将该方法应用到FDT/DTM（Field Device Tool/Device Type Manager）设备管理系统中，对NCS4000水循环控制的压力传感器进行故障诊断，数值实验表明该算法具有实效性。

关键词: 核fisher, 模糊模式识别, 传感器故障诊断, 现场管理工具/设备类型管理器（FDT/DTM）