柴油机是舰船的主要动力装置，针对传统故障诊断方法不能有效提取柴油机故障特征和实现在线诊断的缺点，提出一种基于小波包振动谱图像的柴油机在线故障诊断新方法．该方法首先用小波包对采集到的柴油机振动信号进行分析生成小波包振动谱图；然后利用双线性内插值方法对生成的振动谱图进行数据降维，对降维后的振动谱图进行灰度共生矩阵纹理特征参数提取；最后用分类器对特征参数进行识别，完成故障诊断。将该方法应用于柴油机气门间隙的故障诊断实例中，结果表明，基于小波包振动谱图像的柴油机在线故障诊断方法能快速高效的诊断出气门间隙故障，识别准确率高达 99.17%，仅耗时 0.24 s，为内燃机故障在线诊断探索了一条新途径。
Diesel engine is the main power device of ship, for the disadvantages of traditional methods can't effectively extract fault feature and can't realize the fault online diagnosis, this paper proposes a new diesel engine online fault diagnosis method based on wavelet packet vibration image. Firstly, using the wavelet packet to the collected diesel engine vibration acceleration signals to get vibration images; then using bilinear interpolation method in the generated vibration images for data dimension reduction, then using the gray level co-occurrence matrix for the texture feature parameter extraction; finally with classifier accomplish fault diagnosis. This method was applied to fault diagnosis of diesel engine valve clearance, the results show that the fault can be quickly and efficiently diagnosed by diesel engine online fault diagnosis method based on wavelet packet vibration image, recognition accuracy rate can reach 99.17 percent, only consuming 0.24 S, explored a new way for diesel engine online fault diagnosis.
2016,38(8): 128-133 收稿日期：2016-5-13
DOI：10.3404/j.issn.1672-7619.2016.08.027
分类号：U664.121;TH212;TH213.3
基金项目：国家自然科学基金资助项目（51405498）；陕西省自然科学基金资助项目（2013JQ8023）；中国博士后基金资助项目（2015M582642）
作者简介：岳应娟(1973-),女,教授,从事压力容器检测和机电设备状态检测及故障诊断的研究工作。
参考文献：
[1] DURAK L, ARIKAN O. Short-time Fourier transform: Two fundamental properties and an optimal implementation[J]. IEEE Transactions on Signal Processing, 2003, 51(5): 1231-1242.
[2] DJUROVIĆ I, SEJDIĆ E, JIANG J. Frequency-based window width optimization for S-transform[J]. AEU-international Journal of Electronics and Communications, 2008, 62(4): 245-250.
[3] SMITH C, AKUJUOBI C M, HAMORY P, et al. An approach to vibration analysis using wavelets in an application of aircraft health monitoring[J]. Mechanical Systems and Signal Processing, 2007, 21(3): 1255-1272.
[4] QAZI S, GEORGAKIS A, STERGIOULAS L K, et al. Interference suppression in the Wigner distribution using fractional Fourier transformation and signal synthesis[J]. IEEE Transactions on Signal Processing, 2007, 55(6): 3150-3154.
[5] MARGENAU H, HILL R N. Correlation between measurements in quantum theory[J]. Progress of Theoretical Physics, 1961, 26(5): 722-738.
[6] 王珍, 马孝江. 局域波时频法在柴油机缸套活塞磨损诊断中的应用研究[J]. 内燃机学报, 2002, 20(2): 157-160.
[7] 蔡艳平, 李艾华, 王涛, 等. 基于 EMD-Wigner-Ville 的内燃机振动时频分析[J]. 振动工程学报, 2010, 23(4): 430-437.
[8] 孙斌, 万鹏威, 陶达, 等. 基于自适应最优核时频分布的鸟类识别[J]. 数据采集与处理, 2015, 30(6): 1187-1195.
[9] 葛哲学, 陈仲生. Matlab 时频分析技术及其应用[M]. 北京: 人民邮电出版社, 2006.
[10] 郭亚. 振动信号处理中的小波基选择研究[D]. 合肥: 合肥工业大学, 2003.
[11] 郑红, 李钊, 李俊. 灰度共生矩阵的快速实现和优化方法研究[J]. 仪器仪表学报, 2012, 33(11): 2509-2515. ZHENG Hong, LI Zhao, LI Jun. Study on fast implementation and optimal methodof gray level co-occurrence matrix[J]. Chinese Journal of Scientific Instrument, 2012, 33(11): 2509-2515.
