【作者】 张周锁； 周晓宁； 成玮；

【Author】 Zhang Zhousuo Zhou Xiaoning Cheng Wei (State Key Laboratory for Manufacturing Systems Engineering,Xi’an Jiaotong University,Xi’an 710049,China)

【机构】 西安交通大学机械制造系统工程国家重点实验室；

【摘要】 蚁群算法具有正反馈、分布式、并行处理、强鲁棒性等特点.本文在介绍蚁群算法基本原理的基础上,构建了一种多蚂蚁并行自适应蚁群聚类算法。将该算法应用于机车轮对轴承故障识别的正确率为87%,表明蚁群聚类算法用于故障分类具有良好的效果,是机械故障智能诊断的一种有效方法。更多还原

【Abstract】 Ant colony algorithm is distributed,parallel,robust and based on positive feedback.Principle of basic ant colony algorithm is introduced,and an adaptive clustering algorithm based on multi-ants parallel mechanism is constructed in this paper.The adaptive clustering algorithm is applied to fault classification of the locomotive wheel-paired bearings,and the accuracy rate of classification is 87%.Research results show the algorithm is effectual on practical fault diagnosis.更多还原