改进的阴性选择算法在机械故障诊断中的应用  

The Improved Negative Selection Algorithm and Its Application in Mechanical Fault Diagnosis

作　　者：白转伟 董增寿[1] 石慧[1] 苏向阳[1] 

机构地区：[1]太原科技大学电子信息工程学院,太原030024

出　　处：《太原科技大学学报》2017年第5期349-354,共6页Journal of Taiyuan University of Science and Technology

基　　金：国家自然基金面上项目(20121079);太原科技大学博士科研启动基金(20132021)

摘　　要：针对复杂大型设备故障诊断准确率低的问题,提出一种改进阴性选择算法的故障诊断方法。在改进可变半径实值阴性选择算法(V-detector)中,训练开始阶段通过蒙特卡罗算法寻找半径尽可能大的检测器,然后引入覆盖阈值,通过阈值判定减少了无效检测器的产生,提高了算法的检测率。由于V-detector算法只能识别自我和非我,建立了免疫聚类的故障诊断模型,并将改进V-detector免疫聚类故障诊断模型应用于齿轮故障诊断中。实验结果表明:改进的V-detector算法可以有效的避免了检测器重复覆盖造成检测器数目的增加,提高了非自体区域的覆盖率,比未改进的V-detector的免疫聚类诊断方法有较高的准确率。The accuracy of large equipment fault diagnosis based on negative selection algorithm is low. The fault diagnosis method of improved negative selection algorithm is proposed. During the improvement of real-valued negative selection algorithm with variable radius detector,the detector radius as large as possible is set by Monte Carlo algorithm. The invalid detector is subdued and the detection rate of the algorithm is improved by introducing detector threshold. The V-detector algorithm can only identify self and non-self,so the fault diagnosis model of immune clustering algorithm is established. The fault diagnosis model based on the improved V-detector immune clustering is applied to gear fault diagnosis. The experimental results show that the improved V-detector algorithm effectively avoids the addition of detector number and improves non-self coverage. The fault diagnosis model based on based on the improved V-detector immune clustering has the better fault diagnosis effect than that based on the no improved V-detector immune clustering in fault diagnosis of gear.

关 键 词：阴性选择算法 免疫聚类算法 故障诊断模型 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]