基于支持向量机的机械活塞疲劳信号检测方法

Detection Method of Mechanical Piston Fatigue Signal Based on Support Vector Machine

为避免机械活塞工作疲劳导致设备出现故障的问题,提出基于支持向量机的机械活塞疲劳信号检测方法。首先对机械活塞结构及工作原理进行分析,了解机械负载状态下活塞产生疲劳信号的原因,获取与疲劳信号相关的参数;然后将这些参数代入活塞理论损伤模型中,建立描述疲劳信号释放过程的疲劳损伤模型;最后在模型拟合端结合支持向量机,对疲劳信号进行分类,实现机械活塞疲劳信号的精准检测。试验结果表明,所提方法检测效率高、检测率高,具有一定应用价值。

In order to avoid the problem of equipment failure caused by working fatigue of mechanical piston,a method for detecting fatigue signal of mechanical piston based on support vector machine is proposed.First,the structure and working principle of the mechanical piston are analyzed to understand the reasons for the fatigue signal of the piston under mechanical load,obtain the parameters related to the fatigue signal,and then substitute these parameters into the theoretical damage model of the piston to establish the fatigue signal describing the release process of the fatigue signal.The damage model is finally combined with the support vector machine at the model fitting end to classify the fatigue signal,so as to realize the accurate detection of the fatigue signal of the mechanical piston.The experimental results show that the proposed method has high detection efficiency and high detection rate,and has certain application value.