研究传感器系统故障诊断效率问题.针对传统故障诊断因传输信息大,速度慢,造成故障,定位不清.传统的方法提取的传感器系统特征信息不全面,导致诊断精度与速度不高.为有效提高传感器系统故障诊断的效率和精度,提出了一种能量信息熵的支持向量机系统故障诊断方法.故障主要难点技术问题在于参数选择优化问题.算法首先利用小波包对传感系统故障信号进行小波包分解,并提取小波包能量信息熵,以此构建输入特征向量；接着采用了支持向量机方法进行非线性特征向量提取,最后以特征向量来建立支持向量机智能化诊断模型.仿真结果表明,改进方法在所有参比模型中精度最高,能高效地对传感器故障进行检测与定位.具有较强的泛化能力,同时缩短了故障诊断时间.%The paper deals with efficiency of sensor system fault diagnosis. The characteristics information of linear sensor system extracted by traditional fault diagnostic methods is not comprehensive, and results in low diagnostic accuracy and speed. To effectively improve the efficiency and accuracy, the authors proposed a fault diagnosis method based on support vector machine of energy information entropy. Firstly, the method decomposed the fault signal of the sensor system and extracted the wavelet packet energy entropy to build input feature vector, then used support vector machine to extract nonlinear feature vector, and finally built the intelligent diagnosis model of support vector machine with the feature vector. The simulation results showed that the method is effective in sensor fault detecting and localizating, has good generalization ability, and reduces troubleshooting time.
展开▼
