基于节点优化型DAG-LDM的机组滚动轴承故障诊断方法.PDF

第xx 卷第x 期 控 制 与 决 策 Vol.xx No.x xxxx 年 x 月 Control and Decision xxx. xxxx DOI: 10.13195/j.kzyjc.2017.1657 基于节点优化型DAG-LDM 的机组滚动轴承故障诊断方法 刘朝华 , 孟旭东 , 陆碧良 , 李小花 , 童成意 (1. 湖南科技大学信息与电气工程学院，湖南湘潭411201 ；2. 长沙师范学院信息与工程系，长沙410100 ) 摘 要: 滚动轴承作为风电机组的关键部件，对于整个机组的安全运行起着决定性作用。针对机组滚动轴承故障 诊断问题，本文提出了一种节点优化型有向无环图大间隔分布机（O-DAG-LDM ）的故障诊断方法。结合DAG 多分类扩展性能与LDM 二分类器泛化性能的优点，本文构建了一种面向滚动轴承故障诊断的DAG 结构扩展式 LDM 多分类器方法。在DAG-LDM 算法框架下，利用优化算法对DAG 节点进行优化排列以减小随机排布引起 的累积误差，提高了LDM 故障分类准确率。实验表明，与其他主流智能诊断方法相比较，本文所提的节点优化 型DAG-LDM 故障诊断方法具有较高的准确率和更好的抗噪性能。 关键词: 有向无环图；大间隔分布机；多分类器；节点优化；滚动轴承；故障诊断 中图分类号: TP13 文献标志码: A Fault diagnosis method of wind turbine rolling bearing based on a node optimizedDAG-LDM LiuZhaohua ,MengXudong ,LuBiliang ,LiXiaohua ,TongChengyi (1.School of Information and Electrical Engineering, Hunan University of Science and Technology, Hunan Xiangtan 411201; 2.Department of Information and Engineering, Changsha Normal University, Changsha 410100) Abstract: As a key component, the rolling bearing plays a decisive role in the safe operation of the whole wind turbine. To solve the problem of fault diagnosis in rolling bearings, a fault diagnosis method based on optimized directed acyclic graph combing with large margin distribution machine (named O-DAG-LDM) is proposed in this paper. Combining the advantages of DAG multi-class scalable features with the generalization performance of LDM two-classifier in this paper, a DAG structure extended LDM multiple classifier method for rolling bearing fault