基于小波包和支持向量机的传感器故障诊断方法

Sensor Fault Diagnosis Based on Wavelet Packet and Support Vector Machines

针对自确认压力传感器的故障诊断问题,提出了一种基于小波包变换和支持向量机的传感器故障诊断方法。该方法对传感器输出信号进行三层小波包分解,提取各个节点的小波包系数,对每个节点的小波包系数通过一定的削减算法增强故障特征,然后利用重构的时域信号计算各个节点的能量以及整个信号的削减比作为特征向量,以此作为输入来建立支持向量多分类机,判断传感器的故障类型。对自确认压力传感器、温度和流量传感器的故障诊断结果表明,该方法能有效地应用于传感器的故障诊断中。

To solve the fault diagnosis problem of self-validating pressure sensor, a sensor fault diagnosis approach based on wavelet packet transform and support vector machines is proposed. After a three-level decomposition of wavelet packet, the coefficients of each node are achieved. With some cutting algorithm, the reconstructed signals with fault character are strengthened. The energy of each node is calculated with reconstructed signals, and the average cutting ratios of all nodes are regarded as the feature vector. The support vector machines for multi-classification used as fault classifiers are established to identify the condition and fault pattern of the sensor. The results of fault diagnosis on self-validating pressure sensors, temperature and flow sensor show that the proposed approach can be applied to the sensor fault diagnosis effectively.