首页  |  期刊简介  |  期刊荣誉  |  编委会  |  现任主编  |  投稿指南  |  下载中心  |  期刊征订
中文核心期刊
Ei Compendex收录期刊
中国科学引文数据库来源期刊
中文科技期刊数据库收录期刊
国际刊号:1004-6801
国内刊号:32-1361/V
用户登录
  E-mail:  
  密  码:  
  作者 审稿  
  编辑 读者  
期刊向导
联系方式
  • 主管:中华人民共和国工业
              和信息化部
  • 主办:南京航空航天大学
              全国高校机械工程
              测试技术研究会
  • 国际刊号:1004-6801
  • 国内刊号:32-1361/V
  • 地址:南京市御道街29号
  • 电话:025-8489 3332
  • 传真:025-8489 3332
  • E-mail:qchen@nuaa.edu.cn
  • 邮编:210016
强差异性神经网络集成的转子故障识别方法
Method of Rotor Fault Identification Based on Strong Differential Ensemble Neural Network
  
DOI:10.16450/j.cnki.issn.1004?6801.2021.06.010
中文关键词:  集成学习  神经网络  转子  故障诊断
英文关键词:ensemble learning  neural network  rotor  fault diagnosis
基金项目:国家自然科学基金资助项目(51675253);国家重点研发计划资助项目(2016YFF0203303?04);兰州理工大学红柳一流学科建设资助项目
作者单位
马森财, 赵荣珍, 吴耀春 (兰州理工大学机电工程学院 兰州730050) 
摘要点击次数: 15
全文下载次数: 1
中文摘要:
      针对误差反向传播(back propagation,简称BP)神经网络在作为传统Bagging集成学习机中的基分类器时,存在相互之间差异性偏低的问题,引入一种特征扰动法对集成学习机的分类性能进行改进。首先,将Relief?F特征评估算法和改进轮盘赌选择法进行结合,并设置基分类器的数目为30个,从转子故障特征集中选择出30个特征子集,每个特征子集的故障特征维数为30;其次,将训练集和测试集分别投影在对应的30个故障特征子集上,得到对应于30个基分类器的系列训练子集和测试子集,通过此方式实现了特征扰动环节;最后,利用Bagging集成学习机中自带的自助采样法对各训练子集进行处理,使其在最终输入至各基分类器时在特征空间和样本集合上都具有一定的差异性,间接使训练后的基分类器之间显示出更高的差异性,让最终的分类结果可信度更高。用一种低维双跨转子故障数据集对该集成学习方法进行类别辨识的结果表明,本方法能够显著提高BP网络的辨识准确率,并且具有良好的抗干扰性能。
英文摘要:
      Aiming at the problem that the difference among BP neural networks as the base classifier in Bagging ensemble learning is small, a feature perturbation method is Keywords ensemble learning; neural network; rotor; fault diagnosis introduced to improve the classification performance of the model of ensemble learning. Firstly, the Relief-F feature evaluation algorithm is integrated with the improved roulette wheel selection algorithm and the number of base classifiers is set to thirty. Next, thirty feature subsets, where the feature dimension are thirty, are selected from the rotor fault feature set. Then, the training set and the test set are respectively projected on the corresponding thirty fault feature subsets to obtain a series of training and test subsets corresponding to the thirty base classifiers, which realize the feature perturbation. Afterwards, each training subset is processed using the self-service sampling method (bootstrap sampling) included in the Bagging ensemble learning machine. Thus, they has certain differences in the feature space and sample set when they are finally input to each base classifier, which indirectly makes the trained base classifiers show higher differences, so as to achieve the purpose of making the final classification results more credible. Moreover, a low-dimensional double-span rotor fault data set is used to classify in the ensemble learning method. The results show that this method can significantly improve the accuracy of class identification of the BP network. In addition, it also has good performance in terms of anti-interference.
查看全文  查看/发表评论  下载PDF阅读器
关闭

Copyright @2010-2015《振动、测试与诊断》

地址:南京市御道街29号        邮编:210016

电话:025-8489 3332      传真:025-8489 3332       E-mail:qchen@nuaa.edu.cn

您是本站第2771798位访问者 本站今日一共被访问115

技术支持:北京勤云科技发展有限公司