I.C. Engine Fault Diagnosis Based on Discrete Generalized S-transformation and TD-2DPCA

Abstract

Abstract: For the problems of fault diagnosis of I.C. engines, a method was proposed, which is consisted of discrete generalized S-transformation and TD-2DPCA. First of all, vibration spectrum images of cylinder head vibration signals were generated by discrete generalized S transform. Secondly, image matrix was bidirectional compressed by TD-2DPCA to reduce sizes of feature coefficient matrix effectively. Lastly, these feature matrixes obtained from image projects were served as enters of nearest neighbor classifier, which was used to achieve fault types' division. The method was applied to diagnosis example of the vibration signals of valve mechanism eight operating modes, comparisons of different time-frequency characterizations and feature extraction methods were carried out. The results show that the proposed method provides a new way for fault diagnosis of I.C. engines.

Key words: internal combustion(I.C.) engine, discrete generalized S-transformation, two-directional two dimensional principal components analysis(TD-2DPCA), classification recognition

摘要： 针对内燃机气阀机构的故障诊断问题，提出一种将离散广义S变换和双向二维主成分分析（TD-2DPCA）相结合的诊断方法。该方法首先利用离散广义S变换将内燃机缸盖振动信号生成振动谱图像，然后利用TD-2DPCA对图像进行特征提取，有效减小特征系数矩阵的维数，最后，通过最近邻分类器进行分类识别。将该方法应用于内燃机气阀机构8种工况的诊断实例中，对比不同时频表征及特征提取方法的计算效率和识别精度，结果表明该方法可为内燃机故障诊断提供一条新途径。

关键词: 内燃机, 离散广义S变换, 双向二维主成分分析, 分类识别

CLC Number:

TK428

ZHANG Shixiong;CAI Yanping;SHI Linsuo;WANG Xu. I.C. Engine Fault Diagnosis Based on Discrete Generalized S-transformation and TD-2DPCA[J]. China Mechanical Engineering.

张世雄;蔡艳平;石林锁;王旭. 基于离散广义S变换与双向二维主成分分析的内燃机故障诊断[J]. 中国机械工程.

References

[1]胡振邦,许睦旬,姜歌东,等.基于小波降噪和短时傅里叶变换的主轴突加不平衡非平稳信号分析[J].振动与冲击, 2014, 33(5):20-24.
HU Zhenbang, XU Muxun, JIANG Gedong, et al. Analysis of Unbalanced Non-stationary Signal of Spindle Based on Wavelet Denoising and Short-time Fourier Transform[J]. Vibration and Shock, 2014, 33(5):20-24.
[2]岳应娟,孙刚,蔡艳平.基于小波包振动谱图的柴油机在线故障诊断方法[J].舰船科学与技术, 2016, 38(8):128-133.
YUE Yingjuan, SUN Gang, CAI Yanping. On-line Fault Diagnosis Method of Diesel Engine Based on Wavelet Packet Vibration Spectrum[J]. Ship Science and Technology, 2016, 38(8):128-133.
[3]蔡艳平,李艾华,石林锁,等. 基于EMD-WVD振动谱时频图像SVM识别的内燃机故障诊断[J].内燃机工程, 2012, 33(2): 72-79.
CAI Yanping, LI Aihua, SHI Linsuo, et al. Fault Diagnosis of Internal Combustion Engine Based on EMD-WVD Vibration Spectrum Time-frequency Image SVM Recognition[J]. Internal Combustion Engine Engineering, 2012,33(2):72-79.
[4]李志农,朱明,龙盛蓉.新非平稳信号处理方法——自适应径向墨西哥草帽核时频分布[J].振动与冲击, 2015, 34(10): 184-190.
LI Zhinong, ZHU Ming, LONG Shengrong. New Non-stationary Signal Processing Method—Adaptive Radial Mexican Straw Kernel Time-frequency Distribution[J]. Vibration and Shock, 2015, 34(10):184-190.
[5]STOCKWELL R G, MANSINHA L, LOWE R P. Localization of the Complex Spectrum: the S Transform[J]. IEEE Transactions on Signal Processing, 1996, 44(4): 998-1001.
[6]STANKOVIL. A Measure of Some Time-frequency Distributions Concentration[J]. Signal Processing, 2001, 81(3): 621-631.
[7]郭远晶,魏燕定,周晓军,等. S变换用于滚动轴承故障信号冲击特征提取[J]. 振动、测试与诊断, 2014, 34(5): 818-822.
GUO Yuanjing, WEI Yanding, ZHOU Xiaojun, et al. S-transform is Used to Extract the Impact Characteristics of Rolling Bearing Fault Signal[J]. Vibration, Testing and Diagnosis, 2014, 34(5): 818-822.
[8]胡广书.现代信号处理教程[M]. 2版.北京：清华大学出版社, 2015.
HU Guangshu. Modern Signal Processing Tutorial[M]. 2nd ed. Beijing: Tsinghua University Press,2015.
[9]LIU K, CHENG Y Q, YANG J Y. Algebraic Feature Extraction for Image Recognition Based on an Optimal Discriminant Criterion[J]. Pattern Recognition, 1993, 26(6): 903-911.
[10]YANG J, ZHANG D, FRANGI A F, et al. Two-dimensional PCA: a New Approach to Appearance-based Face Representation and Recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(1): 131-137.
[11]陈伏兵,陈秀宏,张生亮,等.基于模块2DPCA的人脸识别方法[J]. 中国图象图形学报, 2006, 11(4): 580-585.
CHEN Fubing, CHEN Xiuhong, ZHANG Shengliang, et al. Face Recognition Method Based on Module 2DPCA[J]. Journal of Image and Graphics, 2006, 11(4): 580-585.
[12]李巍华,林龙,单外平.基于广义S变换与双向2DPCA的轴承故障诊断[J]. 振动、测试与诊断, 2015, 35(3): 499-506.
LI Weihua, LIN Long, SHAN Waiping. Bearing Fault Diagnosis Based on Generalized S-Transform and Bidirectional Principal Components Analysis[J]. Vibration, Testing and Diagnosis, 2015, 35(3): 499-506.
[13]LI M, YUAN B. 2D-LDA: a Statistical Linear Discriminant Analysis for Image Matrix[J]. Pattern Recognition Letters, 2005, 26(5): 527-532.
[14]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.
XU Guogen, JIA Ying. Realization of Pattern Recognition and Intelligent Computing[M]. Beijing: Beijing University of Aeronautics and Astronautics Press, 2012.
[15]夏勇,商斌梁,张振仁,等.基于时序分析与神经网络的气阀机构故障诊断[J]. 机械设计与研究, 2001,17(1):71-74.
XIA Yong, SHANG Binliang, ZHANG Zhenren, et al. Fault Diagnosis of Valve Mechanism Based on Time Series Analysis and Neural Network[J]. Mechanical Design and Research, 2001,17(1):71-74.
[16]王成栋,魏瑞轩,张优云,等.模糊函数图像与概率网络在柴油机气阀故障诊断中的应用[J]. 内燃机工程, 2004, 25(5): 19-23.
WANG Chengdong, WEI Ruixuan, ZHANG Youyun, et al. Application of Fuzzy Function Iimage and Probabilistic Network in Diesel Engine Valve Fault Diagnosis[J]. Internal Combustion Engine Engineering, 2004, 25(5): 19-23.