基于中智KNN的齿轮箱故障诊断方法

PDF(962 KB)

振动与冲击 ›› 2019, Vol. 38 ›› Issue (20) : 148-153.

论文

基于中智KNN的齿轮箱故障诊断方法

王栋璀 ,丁云飞1，朱晨烜1

作者信息 +

A fault diagnosis method for gearbox based on neutrosophic K-Nearest Neighbor

WANG dongcui1 DING yunfei1 ZHU chenxuan1

Author information +

文章历史 +

摘要

齿轮箱在旋转机械设备中应用广泛,研究齿轮箱的故障诊断方法意义重大。为提高齿轮箱故障的预警诊断准确度，提出了基于中智KNN（Neutrosophic K-Nearest Neighbor，NKNN）的齿轮箱故障诊断方法。该方法首先利用小波包对信号特征进行提取，并构建出故障样本集，随后借助中智理论对样本的特征权重进行重新分配，建立起基于中智KNN决策规则下的故障诊断模型，并提出了中智划分的概念。实验表明，该方法有效地提升了分类精度和鲁棒性，弥补了传统KNN同贡献权重分配的缺陷，其中智划分的结果可以作为分析齿轮箱混合故障诊断的参考依据。

Abstract

It is valuable to study the fault diagnosis method for the gearbox as gearboxes are widely used in rotating machinery.In order to improve the accuracy of diagnosis, a neutrosophic K-nearest-neighbor-based fault diagnosis method was presented for gearbox.Firstly, the method uses the wavelet packet to extract the signal features and constructs a fault sample set.Then, with the help of the neutrosophic theory, the feature weights of the samples are redistributed, and finally the fault diagnosis model based on the KNN decision rules was established, and the concept of the neutrosophic partition was proposed.Experiments show that the proposed method can improve the accuracy of classification and robustness effectively, and make up the shortcomings of the weight distribution.

导出引用

王栋璀,丁云飞1，朱晨烜1. 基于中智KNN的齿轮箱故障诊断方法[J]. 振动与冲击, 2019, 38(20): 148-153

WANG dongcui1 DING yunfei1 ZHU chenxuan1 . A fault diagnosis method for gearbox based on neutrosophic K-Nearest Neighbor[J]. Journal of Vibration and Shock, 2019, 38(20): 148-153

参考文献

[1] Xihui Liang, Ming J. Zuo, Zhipeng Feng. Dynamic modeling of gearbox faults: A review[J]. Mechanical Systems and Signal Processing, 2018, 98: 852-876.
[2] 刘凡, 张昀,姚晓,等.基于K近邻算法的换流变压器局部放电模式识别[J]. 电力自动化设备，2013, 33(05): 89-93.
      LIU Fan, Zhang Yun, YAO Xiao,et al.Recognition of PD mode based on KNN algorithm for converter transformer [J]. Electric Power Automation Equipment, 2013, 33(05): 89-93.
[3] 孙斌, 刘立远, 牛翀. 基于局部切空间排列和K-最近邻分类器的转子故障诊断方法[J]. 中国机械工程,2015, 26(01): 74-78.
SUN Bin, LIU Liyuan, NIU Chong. Rotor fault diagnosis methods based on Local Tangent Space Alignment and K-nearest neighbor[J]. China Mechanical Engineering,       2015,26(01): 74-78.
[4] 姜景升, 王华庆, 柯燕亮, 等. 基于LTSA与K-最近邻分类器的故障诊断[J]. 振动与冲击, 2017, 36(11): 134-139.
    JIANG Jingsheng，WANG Huaqing，KE Yanliang，et al. Fault diagnosis based on LTSA and K-Nearest Neighbor classifier[J]. Journal of Vibration and Shock. 2017, 36(11): 134-139.
[5] 侯平智, 张明, 徐晓滨, 等. 基于K近邻证据融合的故障诊断方法[J]. 控制与决策, 2017, 32(10): 1767-1774.
         HOU Ping-zhi, ZHANG Ming, XU Xiao-bin,et al. Fault diagnosis based on KNN evidence fusion[J]. Control and Decision. 2017, 32(10): 1767-1774.
[6] 王雪冬，赵荣珍，邓林峰. 基于KSLPP与RWKNN的旋转机械故障诊断[J]. 振动与冲击, 2016, 35(08): 219-223.
    WANG Xue-dong, ZHAO Rong-zhen, DENG Lin-feng. Rotating machinery fault diagnosis based on KSLPP and RWKNN[J]. Journal of Vibration and Shock. 2016, 35(08): 219-223.
[7] 陈法法, 汤宝平, 苏祖强. 基于等距映射与加权KNN的旋转机械故障诊断[J]. 仪器仪表学报, 2013, 34(01): 215-220.
    CHEN Fafa, TANG Baoping, SU Zuqiang. Rotating machinery fault diagnosis based on isometric mapping and weighted KNN[J]. Chinese Journal of Scientific Instrument. 2013, 34(01): 215-220.
[8] Keller J M, Gray M R, Givens J A. A fuzzy k-nearest neighbor algorithm[J]. IEEE Transactions on Systems, Man, and Cybernetics, 1985, 15(4): 580 -585.
[9] 杜海莲, 吕锋, 辛涛, 等. 基于证据理论的优化集成分类器融合算法及应用[J]. 化工学报, 2012, 63(09): 2877-2881.
    DU Hailian, Lü Feng, XIN Tao, et al. Algorithm and application of optimal multi-classifier combination based on evidence theory[J]. Ciesc Journal, 2012, 63(9): 2877-2881.
[10] Smărăndache F. Neutrosophic probability, set and logic[J]. Bull. transilv. univ. braov Ser. b, 2016: 41-48.
[11] Smarandache F. Introduction to Neutrosophic Measure, Neutrosophic Integral, and Neutrosophic Probability[J]. Computer Science, 2013, 22d(1): 13-25.
[12] Broumi S, Talea M, Smarandache F, et al. Decision-making method based on the interval valued neutrosophic graph[C]. Future Technologies Conference. IEEE, 2017.
[13] Kandasamy W B V, Smarandache F. Basic neutrosophic algebraic structures and their application to fuzzy and neutrosophic models[M]. Books On Demand - Proquest, 2004.
[14] 于志伟, 苏宝库, 曾鸣. 小波包分析技术在大型电机转子故障诊断系统中的应用[J]. 中国电机工程学报, 2005, 25(22): 158-162.
    YU Zhiwei, SU Baoku, ZENG Ming. Application of wavelet packet in fault diagnosis system of large scale DC motor rotor[J]. Proceedings of the CSEE, 2005, 25(22):158-162.
[15] 周祥鑫, 王小敏, 杨扬, 等. 基于小波阈值的高速道岔振动信号降噪[J]. 振动与冲击, 2014, 33(23): 200-206.
ZHOU Xiangxin, WANG Xiaomin, YANG Yang, et al. De-noising of high-speed turnout vibration signals based on wavelet threshold[J]. Journal of Vibration and Shock, 2014, 33(23):200-206.
[16] 许国根, 贾瑛. 模式识别与智能计算的Matlab实现[M]. 北京: 北京航空航天大学出版社, 2012.
[17] 汪庆华, 刘江炜, 张兰兰. 交叉验证K近邻算法分类研究[J]. 西安工业大学学报, 2015, 35(2): 119-124.
WANG Qinghua, LIU Jiangwei, ZHANG Lanlan. Study on the Classification of K-Nearest Neighbor Algorithm[J]. Journal of Xian Technological University, 2015, 35(2): 119-124.