[1]陈立伟,黄璐,齐传斌.基于遗传算法优化的相关向量机的燃机涡轮叶片故障诊断[J].应用科技,2016,43(02):70-74.[doi:10.11991/yykj.201506026]
 CHEN Liwei,HUANG Lu,QI Chuanbin.Fault diagnosis for gas turbine blades based on the relevance vector machine optimized by genetic algorithm[J].Applied science and technology,2016,43(02):70-74.[doi:10.11991/yykj.201506026]
点击复制

基于遗传算法优化的相关向量机的燃机涡轮叶片故障诊断(/HTML)
分享到:

《应用科技》[ISSN:1009-671X/CN:23-1191/U]

卷:
第43卷
期数:
2016年02期
页码:
70-74
栏目:
动力与能源工程
出版日期:
2016-04-05

文章信息/Info

Title:
Fault diagnosis for gas turbine blades based on the relevance vector machine optimized by genetic algorithm
作者:
陈立伟 黄璐 齐传斌
哈尔滨工程大学信息与通信工程学院, 黑龙江哈尔滨 150001
Author(s):
CHEN Liwei HUANG Lu QI Chuanbin
College of Information and Communications Engineering, Harbin Engineering University, Harbin 150001, China
关键词:
遗传算法相关向量机神经网络故障诊断涡轮叶片燃气轮机
Keywords:
genetic algorithmrelevance vector machineneural networkfault diagnosisturbine bladegas turbine
分类号:
TK478
DOI:
10.11991/yykj.201506026
文献标志码:
A
摘要:
以遗传算法、相关向量机理论作为理论指导,采用基于遗传算法优化相关向量机算法对提取的特征向量进行故障分类,并通过与未优化的相关向量机、支持向量机、BP神经网络方法对比,结果发现通过遗传算法优化的相关向量机算法的故障分类正确率要高于相关向量机算法、支持向量机算法和BP神经网络的故障分类方法的正确率,仿真实验验证了优化后的算法在燃机涡轮叶片故障诊断中的优越性和可行性。
Abstract:
In this paper, using the theories of genetic algorithm and relevance vector-machine as the theoretical guidance, the optimal relevance vector machine algorithm based on genetic algorithm is used to diagnosis diagnose the extracted eigenvectors, Compared with the unoptimized relevance vector machine, support vector machine, and BP neural network, the simulation results show the faults diagnosis accuracy of the optimal relevance vector machine algorithm based on genetic algorithm is better than the algorithms of relevance vector machine, support vector machine and BP neural network, The experiment results verify the superiority and effectiveness of the optimized algorithm in fault diagnosis of gas turbine blades.

参考文献/References:

[1] 李旭, 徐心和. 遗传算法在故障诊断专家系统中的应用[J]. 控制与决策, 1998, 13(4):377-380.
[2] 史东锋, 屈梁生. 遗传算法在故障特征选择中的应用研究[J]. 振动、测试与诊断, 2000, 20(3):171-176.
[3] 梁化楼, 戴贵亮. 人工神经网络与遗传算法的结合:进展及展望[J]. 电子学报, 1995, 23(10):194-200.
[4] 熊凌, 赵明旺. 基于遗传算法的BP网络全局收敛的混合智能学习算法[J]. 武汉科技大学学报:自然科学版, 2000, 23(2):183-186.
[5] 唐昌盛, 曲建岭, 于建立. 基于支持向量机的航空发动机故障诊断研究[J]. 测控技术, 2008, 27(4):13-14.
[6] 王雪飘, 李学仁, 吴志强. 粗SVM方法及其在发动机故障诊断中的应用[J]. 微计算机信息杂志, 2008, 24(31):189-191.
[7] 杨树仁, 沈洪远. 基于相关向量机的机器学习算法研究与应用[J]. 计算技术与自动化, 2010, 29(1):43-47.
[8] 李敏强, 寇纪凇, 林丹, 等. 遗传算法的基本理论与应用[M]. 北京:科学出版社, 2002.
[9] HOLLAND J H. Adaptation in natural and artificial systems[M]. Ann Arbor:University of Michigan Press, 1975.
[10] CHANG E J, LIPPMANN R P. Using genetic algorithms to improve pattern classification performance[R]. San Mateo:Advance in Neural Information Processing, 1991, 797-803.

相似文献/References:

[1]姜弢,胡佳伟,侯艳丽.一种超宽带脉冲的设计新方法[J].应用科技,2008,35(12):11.
 JIANG Tao,HU Jia-wei,HOU Yan-li.A new approach to UWB pulse design[J].Applied science and technology,2008,35(02):11.
[2]严浙平,黄宇峰,李锋.遗传算法在AUV局部路径规划中的应用研究[J].应用科技,2009,36(02):46.
 YAN Zhe-ping,HUANG Yu-feng,LI Feng.Research on the application of genetic algorithm in localpath planning for AUV[J].Applied science and technology,2009,36(02):46.
[3]王帆,赵春晖,张志.基于克隆选择算法的人脸特征选择[J].应用科技,2009,36(03):11.
 WANG Fan,ZHAO Chun-hui,ZHANG Zh.Feature selection of face recognition based on genetic algorithm[J].Applied science and technology,2009,36(02):11.
[4]兰海,毛晓东,孙洪亮.STL在电网故障诊断遗传算法中的应用研究[J].应用科技,2009,36(09):56.[doi:10.3969/j.issn.1009-671X.2009.09.013]
 LAN Hai,MAO Xiao-dong,SUN Hong-liang.STL applied in genetic algorithm for fault diagnosis of power grid[J].Applied science and technology,2009,36(02):56.[doi:10.3969/j.issn.1009-671X.2009.09.013]
[5]杨雪娇,池海红.一种改进的光条中心提取方法[J].应用科技,2009,36(12):41.[doi:10.3969/j.issn.1009-671X.2009.12.011]
 YANG Xue-jiao,CHI Hai-hong.An improved method of extracting structured light strip center[J].Applied science and technology,2009,36(02):41.[doi:10.3969/j.issn.1009-671X.2009.12.011]
[6]杨奇,王福伟,何蕾,等.摆线针轮行星减速器最佳短幅系数的确定及优化[J].应用科技,2010,37(05):1.[doi:10.3969/j.issn.1009-671X.2010.05.001]
 YANG Qi,WANG Fu-wei,HE Lei,et al.Optimal value and optimal design of short width coefficient of cycloid pin gear planetary reducer[J].Applied science and technology,2010,37(02):1.[doi:10.3969/j.issn.1009-671X.2010.05.001]
[7]王琦,苏畅,姜弢.“巨”型负磁导率材料的优化设计[J].应用科技,2011,38(04):19.[doi:doi:10.3969/j.issn.1009-671X.2011.04.05]
 WANG Qi,SU Chang,JIANG Tao.Optimal design of negative permeability material with “巨”[J].Applied science and technology,2011,38(02):19.[doi:doi:10.3969/j.issn.1009-671X.2011.04.05]
[8]石远鹏,姜建军,郑德宇,等.输电线路巡检的路径规划与建模[J].应用科技,2011,38(11):18.[doi:10.3969/j.issn.1009-671X.2011.18.004]
 SHI Yuanpeng,JIANG Jianjun,ZHENG Deyu,et al.Route planning and modeling of transmission lines inspection[J].Applied science and technology,2011,38(02):18.[doi:10.3969/j.issn.1009-671X.2011.18.004]
[9]王健峰,张磊,陈国兴,等.基于改进的网格搜索法的SVM参数优化[J].应用科技,2012,39(03):28.[doi:10.3969/j.issn.1009-671X.201112016]
 WANG Jianfeng,ZHANG Lei,CHEN Guoxing,et al.A parameter optimization method for an SVM based on improved grid search algorithm[J].Applied science and technology,2012,39(02):28.[doi:10.3969/j.issn.1009-671X.201112016]
[10]吴楚成,边信黔.一种基于遗传算法的AUV动目标避碰规划的方法[J].应用科技,2005,32(05):43.

备注/Memo

备注/Memo:
收稿日期:2015-06-16;改回日期:。
基金项目:黑龙江省自然科学基金项目(F201413);国家自然科学基金项目(61102105).
作者简介:陈立伟(1974-),女,副教授,博士.
通讯作者:陈立伟,E-mail:chenliwei@hrbeu.edu.cn.
更新日期/Last Update: 2016-04-07