首页|业界动态|文献园地|科技期刊|文献翻译|科技论坛|会员中心|网站功能

English 旧版网站 邮箱

中检索

  首页《机械工程学报》2008年7期目录→小样本条件下潜艇机械噪声源的识别

小样本条件下潜艇机械噪声源的识别

 

徐荣武1  何 琳1  章林柯1  贲可荣2

(1. 海军工程大学振动与噪声研究所 武汉 430033;
2. 海军工程大学计算机工程系 武汉 430033)

 

摘要:辨识主要机械噪声源对于潜艇的噪声控制具有重要意义,但由于实际条件下测试的困难和昂贵的试验成本,通常难以获得足够多的训练样本,因此其本质上是一个小样本条件下的模式识别问题。为改善分类系统在小样本条件下的泛化性能,通过引入集成学习的BAGGING方法,分别与现有分类算法如分类与回归树(Classification and regression tree, CART)和物差反传训练(Back-propagation,BP)相结合,提出了B-CART和B-BP算法。进一步,考虑到实际测量中往往同时利用布置在艇体不同部位上的多个通道(加速度传感器、水听器等)来采集数据,以期获得更多关于噪声源的相关信息,基于此先验信息提出了B-CART-M和B-BP-M算法。在此基础上,首先分别对每个通道的数据进行BAGGING集成,并生成该通道的结论,然后对每个通道的结论进行二次投票,从而得到最终分类结果,得到了算法B-CART-M’和B-BP-M’。舱段模型试验结果表明,以上6种算法均能不同程度提高小样本条件下分类系统的性能,其中B-CART-M’和B-BP-M’效果最为明显;对同一算法而言,外壳数据的分类效果最好,远场数据的分类效果最差,内壳和近场数据的分类效果相差不多。给出了算法实际应用时的若干建议。

关键词:噪声源识别  神经网络  分类与回归树  集成学习

中图分类号:U674 TB53

国家自然科学基金(50775218,10674151)和国防科技预研基金(9140A10050506JB1113)资助项目。20070813收到初稿,20080210收到修改稿

 
浏览(下载)论文全文(PDF格式)

 

作者简介:徐荣武,男,1980年出生,博士研究生。研究方向为舰船噪声与振动控制,噪声源识别。
E-mail:rongwu.xu@gmail.com
何琳,男,1957年出生,教授,博士研究生导师,总装备部隐身技术专业组成员。研究方向为舰船噪声与振动控制。
E-mail:helin202@public.wh.hb.cn


参 考 文 献

[1] 王之程,陈宗岐,于沨,等. 舰船噪声测量与分析[M]. 北京:国防工业出版社,2004.
WANG Zhicheng, CHEN Zongqi, YU Feng, et al. Warship noise measuring and analyzing[M]. Beijing:National Defence Industry Press, 2004.
[2] SHIN Y S, ROBINSON J, ROSSANO G. Submarine installed machinery monitoring and diagnostics:a state-of- the-art review[R]. ADA242189, 1991.
[3] 章林柯,何琳,朱石坚. 潜艇主要噪声源识别方法研究[J]. 噪声与振动控制, 2006(4):7-10.
ZHANG Linke, HE Lin, ZHU Shijian. Review on the methods of identification of submarine main noise sources[J]. Noise and Vibration Control, 2006(4):7-10.
[4] ZHANG L, HE L, ZHU S, et al. Identification of the acoustic fault sources of underwater vehicles based on modular structure variable RBF network[J]. Lecture Notes in Computer Science, 2005, 3 496:567-573.
[5] 郭玉滨. 决策树算法研究综述[J]. 电脑知识与技术,2006(1):155-156,160.
GUO Yubin. Study the survey in decision tree algorithm[J]. Computer Knowledge and Technology, 2006(1):155-156,160.
[6] DUNHAM M H. Data mining introductory and advanced topics[M]. NJ, USA:Prentice Hall Press, 2003.
[7] 栾丽华,吉根林. 决策树分类技术研究[J]. 计算机工程, 2004, 30(9):94-96, 105.
LUAN Lihua, JI Genlin. The study on decision tree classification techniques[J]. Computer Engineering, 2004, 30(9):94-96, 105.
[8] BREIMAN L. Classification and regression trees[M]. New York:Chapman & Hall/CRC, 1984.
[9] DIETTERICH T G. Machine learning research:four current directions[J]. AI Magazine, 1997, 18(4):97-136.
[10] 王珏,周志华,周傲英. 机器学习及其应用[M]. 北京:清华大学出版社,2006.
WANG Jue, ZHOU Zhihua, ZHOU Aoying. Machine learning and its application[M]. Beijing:Tsinghua University Press, 2006.
[11] HANSEN L K, SALAMON P. Neural network ensembles[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1990, 12(10):993-1 101.
[12] 李凯,黄厚宽. 小规模数据集的神经网络集成算法研究[J]. 计算机研究与发展, 2006, 43(7):1 161-1 166.
LI Kai, HUANG Houkuan. Study of a neural network ensemble algorithm for small data sets[J]. Journal of Computer Research and Development, 2006, 43(7): 1 161-1 166.
[13] DIETTERICH T G. Ensemble methods in machine learning[J]. Lecture Notes in Computer Science, 2000 (1 857):1-15.
[14] BREIMAN L. Bagging predictors[J]. Machine Learning, 1996, 24(2):123-140.
[15] FREUND Y, SCHAPIRE R E. A decision-theoretic generalization of on-line learning and an application to boosting[J]. Journal of Computer and System Sciences, 1997(55):119-139.
[16] EFRON B, TIBSHIRANI R. Bootstrap methods for standard errors, confidence intervals, and other measures of statistical accuracy[J]. Statistical Science, 1986(1):77.
[17] 周志华,陈世福. 神经网络集成[J]. 计算机学报, 2002, 25(1):1-8.
ZHOU Zhihua, CHEN Shifu. Neural network ensemble[J]. Chinese Journal of Computers, 2002, 25(1):1-8.
[18] DIETTERICH T G. An experimental comparison of three methods for constructing ensembles of decision trees:bagging, boosting, and randomization[J]. Machine Learning, 2000(40):139-157.
[19] 周志华. 神经计算中若干问题的研究[D]. 南京:南京大学, 2000.
ZHOU Zhihua. Contributions to several issues of neural computing[D]. Nanjing:Nanjing University, 2000.
[20] 边肇祺,张学工. 模式识别[M]. 北京:清华大学出版社,1999.
BIAN Zhaoqi, ZHANG Xuegong. Pattern recognition[M]. Beijing:Tsinghua University Press, 1999.
[21] 周志华,曹存根. 神经网络及其应用[M]. 北京:清华大学出版社,2004.
ZHOU Zhihua, CAO Cungen. Neural network and its application[M]. Beijing:Tsinghua University Press, 2004.
[22] WOLPERT D H, MACREADY W G. No free lunch theorems for optimization[J]. IEEE Transactions on Evolutionary Computation, 1997, 1(1):67-82.
[23] UEDA N, NAKANO R. Estimating expected error rates of neural network classifiers in small sample size situations:a comparison of cross-validation and bootstrap[C]// International Conference on Neural Networks, Australia, 1995, 1:101-104.
[24] KOHAVI R. A study of cross-validation and bootstrap for accuracy estimation and model selection[C]// The Fourteenth International Joint Conference on Artificial Intelligence, San Francisco, 1995:1 137-1 145.
[25] TWOMEY J M, SMITH A E. Bias and variance of validation methods for function approximation neural networks under conditions of sparse data[J]. IEEE Transactions on Systems, Man and Cybernetics, Part C, 1998, 28(3):417-430.
[26] 樊养余,孙进才,李平安,等. 基于高阶谱的舰船辐射噪声特征提取[J]. 声学学报, 1999, 24(6):611-616.
FAN Yangyu, SUN Jincai, LI Pingan, et al. Feature extraction of ship-radiated noise using higher-order spectrum[J]. Acta Acustica, 1999, 24(6):611-616.
[27] 李训诰,冯欣欣,戈弋. 舰船辐射噪声的动态识别[J]. 声学学报, 2002, 27(5):443-448.
LI Xungao, FENG Xinxin, GE Yi. Moveable state recognition from ship-radiated noise[J]. Acta Acustica, 2002, 27(5):443-448.
[28] KOHAVI R, JOHN G H. Wrappers for feature subset selection[J]. Artificial Intelligence, 1997, 97(1-2):273-324.
[29] GUYON I, ELISSEEFF A. An introduction to variable and feature selection[J]. Journal of Machine Learning Research, 2003(3):1 157-1 182.
[30] JAIN A, ZONGKER D. Feature selection:evaluation, application, and small sample performance[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 19(2):153-158.
[31] BLUM A L, LANGLEY P. Selection of relevant features and examples in machine learning[J]. Artificial Intelligence, 1997 (97):245-271.
[32] SKURICHINA M, DUIN R P W. Stabilizing classifiers for very small sample sizes[C]// 13th International Conference on Pattern Recognition, Vienna, Austria, 1996, 2:891-896.
[33] RAUDYS S J, JAIN A K. Small sample size effects in statistical pattern recognition:recommendations for practitioners[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1991, 13(3):252-264.

关于我们-联系我们-网站地图-广告服务-人才招聘-加盟合作-法律声明

地址: 中国北京百万庄大街22号  邮编: 100037  电话: 8610-88379907  传真: 8610-68994557
E-mail: cjme@mail.machineinfo.gov.cn  http: // www.cjmenet.com.cn
©2006 版权所有《机械工程学报》编辑部