›› 2016, Vol. 29 ›› Issue (11): 133-.

• 论文 • 上一篇    下一篇

基于FSAACO混合改进算法的蜗轮蜗杆故障识别

杨 雷,朱灵康,高国伟,许 恺,杨 晗,金 昊   

  1. (上海理工大学 机械工程学院,上海 200093)
  • 出版日期:2016-11-15 发布日期:2016-11-24
  • 作者简介:杨雷(1992-),男,硕士研究生。研究方向:信号处理,智能控制。

Worm Gear Fault Identification Based on FSAACO Mixed Improved Algorithm

YANG Lei, ZHU Lingkang, GAO Guowei, XU Kai, YANG Han, JIN Hao   

  1. (School of Mechanical Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China)
  • Online:2016-11-15 Published:2016-11-24

摘要:

针对蜗轮蜗杆故障诊断问题,提出基于FSAACO混合改进算法的蜗轮蜗杆故障识别的研究方法。该方法提出了FSAACO混合改进策略,在谋求一个优势互补的基础上,对算法相关参数优化。同时针对该算法与蜗轮蜗杆故障识别结合构建算法模型问题,提出利用近邻函数准则作理论桥梁策略,寻找一种新的基于FSAACO混合算法的蜗轮蜗杆故障诊断技术研究方法。以WPA40型号的蜗轮蜗杆为测试对象,验证了该研究方法的可行性和有效性。

关键词: 蜗轮蜗杆, 鱼群算法, 蚁群算法, 故障识别, 近邻准则

Abstract:

A new method for fault identification of worm gears based on mixed improved FSAACO (fish swarm algorithmant colony optimization) algorithm is proposed. The method first proposes mixed improved FSAACO strategies to optimize the relevant parameters of the algorithm in seeking a complementary of advantages. Meanwhile, in constructing the algorithm model that combines this algorithm with fault identification for worm gears, a strategy guideline based on the neighbor function theory is proposed, looking for a new fault diagnosis technology for worm gears based on mixed FSAACO algorithm. Worm gears of WPA40 are taken as the test model to testify the feasibility and effectiveness of the research method.

Key words: worm gear, fish swarm algorithm, ant colony optimization, fault identification, neighbor theory

中图分类号: 

  • TP206.3