基于模糊支持向量机的变速器新产品疲劳失效辨识方法  

Study of Fatigue Failure Identification Method for Transmission New Product Based on Fuzzy Support Vector Machine

作　　者：米林[1] 王苏磊 谭伟[1] 张勇 

机构地区：[1]重庆理工大学汽车零部件先进制造技术教育部重点实验室,重庆400054 [2]重庆机电装备技术研究院有限公司,重庆401123

出　　处：《重庆理工大学学报（自然科学）》2017年第5期1-5,共5页Journal of Chongqing University of Technology：Natural Science

基　　金：重庆市科技支撑示范工程资助项目(cstc2014fazktjcsf6003);重庆理工大学科研启动基金资助项目(2015ZD06)

摘　　要：针对变速器试验过程中容易出现一系列如断齿、断轴等影响试验系统设备运行安全的突发性失效问题,为及时准确地辨识出新产品试验过程中的疲劳失效状态,采用基于模糊支持向量机方法,将新产品前期运行特征参数作为训练样本,通过训练得到隶属度函数,对疲劳失效征兆进行模糊化处理确定疲劳失效隶属度。该方法可有效解决新产品缺乏失效特征样本的问题,可准确辨识出变速器新产品疲劳失效状态。试验结果表明:该方法在变速器新产品疲劳失效辨识中具有较高的准确性。A series of unexpected failure of the test system, such as broken teeth, broken shaft, etc. , which affect the operation safety of the test system, is easy to appear in the process of transmissiontest, and for timely and accurate identification of a new product in the process of fatigue test failure, using fuzzy support vector machine method based on the characteristics of the new product, we get the subordinating degree function through training. And we blur the fatigue failure symptom to determine the fatigue failure of membership degree. This method can effectively solve the lack of new product failure characteristics of samples, and have an accurate identification of new products transmission fatigue failure. The test results show that the method has high accuracy in the identification of the fatigue failure of the transmission new products.

关 键 词：模糊支持向量机 疲劳失效 特征辨识 变速器新产品 

分 类 号：U467.497[机械工程—车辆工程]