基于局部切空间排列和最小二乘支持向量机的气缸压力识别

PDF(1536 KB)

振动与冲击 ›› 2020, Vol. 39 ›› Issue (13) : 16-21.

论文

常春1,梅检民1，赵慧敏1，沈虹1，李晓辉2

作者信息 +

Recognition of cylinder pressure based on LTSA-LSSVM

CHANG Chun1， MEI Jianmin1,ZHAO Huimin1,SHEN Hong1,LI Xiaohui2

Author information +

文章历史 +

摘要

为了提高缸盖振动信号恢复气缸压力的识别精度，提出一种基于局部切空间排列（LTSA）和最小二乘支持向量机（LSSVM）的气缸压力识别方法。首先提取缸盖振动信号时域、频域及小波包能量域特征，组成高维特征集，利用LTSA算法提取高维特征集的低维本征流形特征，然后把降维后的特征参数集作为LSSVM模型输入，缸压信号作为LSSVM模型输出，通过多个样本对LSSVM模型进行训练，从而获得气缸压力的重构模型。试验结果表明：基于局部切空间排列和最小二乘支持向量机的气缸压力识别方法具有精度高、泛化能力强等优点。

Abstract

In order to improve the recognition accuracy of cylinder head vibration signal recovery cylinder pressure, a recognition method based on local tangent space arrangement (LTSA) and least squares support vector machine (LSSVM) is proposed. Firstly, the multi-dimensional features of the cylinder head vibration signals were extracted on time-domain, frequency-domain and wavelet packet energy-domain, and the dimension of feature set was reduced by LTSA method. Feature set reduced was used as the input of LSSVM model, and cylinder pressure was used as the output. Then a model for recognition of cylinder pressure was obtained by training the LSSVM model with plurality of samples. The results show that the cylinder pressure recognition method based on local tangent space arrangement and least squares support vector machine has the advantages of high precision and strong generalization ability.

导出引用

常春1,梅检民1，赵慧敏1，沈虹1，李晓辉2. 基于局部切空间排列和最小二乘支持向量机的气缸压力识别[J]. 振动与冲击, 2020, 39(13): 16-21

CHANG Chun1， MEI Jianmin1,ZHAO Huimin1,SHEN Hong1,LI Xiaohui2. Recognition of cylinder pressure based on LTSA-LSSVM[J]. Journal of Vibration and Shock, 2020, 39(13): 16-21

参考文献

[1] 郝志勇,舒歌群,薛远等.内燃机气缸压力振动识别研究[J].内燃机学报,1994,12(1):42-48.
HAO Zhiyong, SHU Gequn, XUE Yuan, et al.An Investigation of Identifying Cylinder Pressure of I. C. Engine by Vibrtation Measurement[J]. Transactions of CSICE,1994,12(1):42-48.
[2] 姚建军,向阳,王志华,丁河青. 基于传递函数法的柴油机气缸压力识别[J]. 武汉理工大学学报(交通科学与工程版),2006,01:70-72.
YAO Jianjun, XIANG Yang, WANG Zhihua, et al. Identification of Diesel Engine Cylinder Pressure Based on Transfer Function[J]. Journal of Wuhan University of Technology (Transportation Science & Engineering), 2006,01:70-72.
[3] 姚建军,向阳,周勇等.基于倒频谱方法的柴油机气缸压力识别[J].航海工程,2006,1:37-39.
YAO Jianjun, XIANG Yang, ZHOU Yong, et al. Identification of cylinder pressure of diesel engine based on the cepstral analysis[J]. Ship & Ocean Engineering,2006,1:37-39.
[4] 张振仁,石林锁,王成栋等.基于小波分析和时序分析的柴油机气缸压力识别[J].内燃机学报,1999,17(2):136-139.
ZHANG Zhenren, SHI Linsuo, WANG Chengdong, et al. Identification of Diesel Cylinder Pressure Based on Wavelet Analysis and Time-Series Analysis[J]. Transactions of CSICE,1999,17(2):136-139.
[5] 陈国金,张云电.基于小波分析ARMA模型的气体压力识别[J].振动工程学报,2002,15(4):484-487.
CHEN Guojin, ZHANG Yundian. Identification of Cylinder Pressure Based on Wavelet Analysis and ARMA Model[J]. Journal of Vibration Engineering,2002,15(4):484-487.
[6] 高洪滨,欧阳光耀,张萍.基于BP神经网络的柴油机气缸压力重构[J]. 内燃机工程,2005,26(1):68-70.
GAO Hongbin, OUYANG Guangyao, ZHANG Ping. Reconstruction of Diesel Engine Cylinder Pressure Based on BP Neural Network[J]. Chinese Internal Combustion Engine Engineering, 2005,26(1):68-70.
[7] 刘建敏,李华莹,乔新勇等.基于缸盖振动信号的气缸压力识别方法研究[J].内燃机工程,2013,34(4):32-37.
LIU Jianmin, LI Huaying, QIAO Xinyong, et al. Engine Cylinder Pressure Identification Method Based on Cylinder Head Vibration Signal[J]. Chinese Internal Combustion Engine Engineering,2013,34(4):32-37.
[8] 纪少波,程勇,唐娟等.基于缸盖振动信号时域特征识别气缸压力的研究[J].内燃机工程,2008,29(2):76-80.
JI Shaobo, CHENG Yong, TANG Juan, et al. Recognition of Cylinder Pressure Based on Time Domain Characteristic of Vibration Signal Measured from Cylinder Head[J]. Chinese Internal Combustion Engine Engineering,2008,29(2):76-80.
[9] Saimurugan K I, Ramachandran V S. Multi Component Fault Diagnosis of Rotational Mechanical System Based on Decision Tree and Support Vector Machine[J]. Expert Systems with Applications, 2011,38:3819-3826.
[10] 张浩然,韩正之,李昌刚.基于支持向量机的非线性系统辨识[J].系统仿真学报,2003,18(1):89-91.
ZHANG Haoran, HAN Zhenzhi, LI Changgang. Support Vector Machine Based Nonlinear Systems Identification[J]. Journal of System Simulation, 2003,18(1):89-91.
[11] 申中杰,陈雪峰,何正嘉等.基于相对特征和多变量支持向量机的滚动轴承剩余寿命预测[J].机械工程学报,2013,42(2): 183-189.
SHEN Zhongjie, CHEN Xuefeng, HE Zhengjia, et al. Remaining Life Predictions of Rolling Bearing Based on Relative Features and Multivariable Support Vector Machine[J]. Journal of Mechanical Engineering,2013,42(2): 183-189.
[12] Zhang Z Y, Zha H Y. Principal manifolds and nonlinear dimensionality reduction via tangent space alignment[J]. SIAM Journal of Scientific Computing,2004,26(1):313-338.
[13] Suykens K, Gestel V, Brabanter D, et al. Least Squares Support Vector Machines[M].Singapore:World Scientific Publishing Company,2002．
[14] 王雷.基于流形学习的滚动轴承故障诊断若干方法研究[D].大连理工大学,2013.
WANG Lei. Research on Rolling Element Bearing Fault Diagnosis Methods Based on Manifold Learing[D]. Dalian University of Technology,2013.
[15] Vahid Ranaee, Ata Ebrahimzadeh, Reza Ghaderi. Application of the PSO–SVM model for recognition of control chart patterns[J]. ISA Transactions,2010,49,577–586.