Application of Kernel Principal Component Analysis Based on Geodesic Distance in Pattern Recognition of Gear Pump

Abstract

Abstract: As traditional Gauss radial basis kernel which adopts the method of calculating Euclidean distances can not describe completely the relationship between the nonlinear vibration sample data, an improved kernel principal component analytic method was proposed. The method substitutes geodesic distance for Euclidean distance in Gauss radial basis kernel, establishes an appraisement function based on scatter of the sort and space between different sorts, and then uses genetic algorithm (GA) to optimize the k parameter within geodesic distance and delta parameter within Gauss radial basis kernel. The gear pump vibration output signals are decomposed into a number of intrinsic mode function (IMF) components and a residue component, and the method calculates ten nondimensional parameters of each IMF and residue component, then using the optimized kernel function to analyze original parameters. The condition recognition result of gear pump vibration signals in different conditions shows that the novel method is effective.

Key words: kernel principal component analysis (KPCA), Gauss radial basis kernel, geodesic distance, genetic algorithm (GA), pattern recognition

CLC Number:

TH137

References

［1］张曦, 阎威武, 赵旭, 等. 基于小波去噪核主元分析和邻近支持向量机的性能监控和故障诊断［J］. 上海交通大学学报, 2008, 42(2): 181185.

ZHANG Xi, YAN Weiwu, ZHAO Xu, et al. Performance monitoring and fault identification based on denoised kernel principal component analysis and proximal support vector machine［J］. Journal of Shanghai Jiaotong University, 2008, 42(2): 181185.

［2］沈志熙, 黄席樾, 马笑潇. 基于EMD多模态特征融合支持向量机的故障诊断［J］. 控制与决策, 2009, 24(6): 889891.

SHEN Zhixi, HUANG Xiyue, MA Xiaoxiao. Fault diagnosis method based on empirical mode decomposition and support vector machine［J］. Control and Decision, 2009, 24(6): 889891.

［3］Lee J M, Yoo C K, Choi S W, et al. Nonlinear process monitoring using kernel principal component analysis［J］. Chemical Engineering Science, 2004, 59(1): 223234.

［4］Kuo P W, Sheng D W. Choosing the kernel parameters for support vector machines by the intercluster distance in the feature space［J］. Pattern Recognition, 2009, 42: 710717.

［5］Wang J H, Xie B L, Xu J J, et al. A fast KPCAbased nonlinear feature extraction method［C］//2009 Second AsiaPacific Conference on Computational Intelligence and Industrial Applications. China: PACIIA, 2009: 232235.

［6］于春梅, 潘泉, 程咏梅, 等. 基于核主元提取的支持向量机辨识［J］. 数学的实践与认识, 2009, 39(1): 132134.

YU Chunmei, PAN Quan, CHENG Yongmei, et al. KPCA based SVM identification of nonlinear system［J］. Mathematics in Practice and Theory, 2009, 39(1): 132134.

［7］史忠植. 神经网络［M］. 北京：高等教育出版社, 2009.

［8］李波. 基于流形学习的特征提取方法及其应用研究［D］. 合肥：中国科学技术大学自动化系, 2008.

［9］魏秀业,潘宏侠,黄晋英, 等. 基于粒子群优化的核主元分析的故障状态识别［J］. 机械科学与技术, 2009, 8(12): 15471549.

WEI Xiuye, PAN Hongxia, HUANG Jinying, et al. Fault condition recognition with kernel principal component analy sis based on particle swarm optimization［J］. Mechanical Science and Technology for Aerospace Engineering, 2009, 28(12): 15471549.

［10］李宏坤, 马孝江. 基于KPCASVM的柴油机状态识别方法的研究［J］. 振动、测试与诊断, 2009,29(1): 4243.

LI Hongkun, MA Xiaojiang. Pattern recognition of diesel engine by using kernel principle component analysis and support vector machine［J］. Journal of Vibration, Measurement & Diagnosis, 2009, 29(1): 4243.

［11］胡金海, 谢寿生. 基于遗传算法的航空发动机性能监控与故障诊断［J］. 推进技术, 2003, 24(3): 198200.

HU Jinhai, XIE Shousheng. Performance monitoring and fault diagnosis of aeroengine based genetic algorithm［J］. Journal of Propulsion Technology, 2003, 24(3): 198200.

［12］龚纯,王正林. 精通MATLAB最优化计算［M］. 北京：电子工业出版社, 2009.

[1]	KANG Jie* (亢洁), DING Jumin (丁菊敏), LEI Tao (雷涛),FENG Shujie (冯树杰), LIU Gang (刘港). Interactive Liver Segmentation Algorithm Based on Geodesic Distance and V-Net [J]. J Shanghai Jiaotong Univ Sci, 2022, 27(2): 190-201.
[2]	GUO Jinyu, LI Wentao, LI Yuan. Adaptive Process Monitoring of Online Reduced Kernel Principal Component Analysis [J]. Journal of Shanghai Jiao Tong University, 2022, 56(10): 1397-1408.
[3]	LI Jie (李杰), LIU Yongzhi (刘勇智), SHAN Chenglong (鄯成龙), DAI Cong (戴聪). Implementation of Simplified Fractional-Order PID Controller Based on Modified Oustaloup's Recursive Filter [J]. Journal of Shanghai Jiao Tong University (Science), 2020, 25(1): 44-50.
[4]	WANG Menghan* (王梦寒), XIAO Guiqian (肖贵乾), WANG Jinqiang (王晋强), LI Zhi (李志). Optimization of Clinching Tools by Integrated Finite Element Model and Genetic Algorithm Approach [J]. Journal of Shanghai Jiao Tong University (Science), 2019, 24(2): 262-272.
[5]	MENG Yu *(孟宇), GAN Xin (甘鑫), WANG Yu (汪钰), GU Qing (顾青). LQR-GA Controller for Articulated Dump Truck Path Tracking System [J]. Journal of Shanghai Jiao Tong University (Science), 2019, 24(1): 78-85.
[6]	JIAO Qinglong (焦庆龙), XU Da (徐达). A Discrete Bat Algorithm for Disassembly Sequence Planning [J]. Journal of Shanghai Jiao Tong University (Science), 2018, 23(2): 276-285.
[7]	DING Siyi,JIN Sun,LI Zhimin,WEI Zhenqi,YANG Fuyong. Deviation Propagation Model and Optimization of Concentricity for Aero-Engine Rotor Assembly [J]. Journal of Shanghai Jiaotong University, 2018, 52(1): 54-62.
[8]	GAO Xiaoting,YANG Dongsheng. Research on Operation Condition Monitoring Method of Intellectual Apparatus Based on Data Driven [J]. Journal of Shanghai Jiaotong University, 2017, 51(9): 1104-1110.
[9]	LI Qing1,LIANG Steven Y1,2,YANG Jianguo1. Bearing Fault Pattern Recognition Using Harmonic Wavelet Sample Entropy and Hidden Markov Model [J]. Journal of Shanghai Jiaotong University, 2016, 50(05): 723-729.
[10]	PAN Qian1*(潘谦), HE Xing1 (何星), CAI Yun-ze1 (蔡云泽),WANG Zhi-hua2 (王治华), SU Fan2 (苏凡). Improved Real-Coded Genetic Algorithm Solution for Unit Commitment Problem Considering Energy Saving and Emission Reduction Demands [J]. Journal of shanghai Jiaotong University (Science), 2015, 20(2): 218-223.
[11]	LIU Changhuia,JIN Suna,LAI Xinmina,LI Feib. Molding and Optimization of Injection Conditions on Shrinkage for Thin-Walled Wax Part Using RSM-GA Method [J]. Journal of Shanghai Jiaotong University, 2015, 49(09): 1380-1386.
[12]	ZHAO Xiuliang,CHENG Yong,WANG Limei. Improvement of SNR of Vibration Response Signal Excited by In-Cylinder Pressure Using Pattern Recognition Method [J]. Journal of Shanghai Jiaotong University, 2015, 49(05): 637-643.
[13]	XU Yan-ran (徐嫣然), ZHAO Jun*(赵俊). Segmentation of Haustral Folds and Polyps on Haustral Folds in CT Colonography Using Complementary Geodesic Distance Transformation [J]. Journal of shanghai Jiaotong University (Science), 2014, 19(5): 513-520.
[14]	FENG Jinzhi1，YU Fan2，ZHENG Songlin1，SUN Tao1，GAO Dawei1. Hierarchy Control Strategy for Active Hydro-Pneumatic Suspension Vehicles Based on Genetic Algorithm [J]. Journal of Shanghai Jiaotong University, 2014, 48(04): 525-531.
[15]	HUANG Qiang1,2 (黄强), LOU Xin-yuan3 (楼新远), WANG Wei4* (王薇), NI Shao-quan1 (倪少权). Research of Order Allocation Model Based on Cloud and Hybrid Genetic Algorithm Under Ecommerce Environment [J]. Journal of shanghai Jiaotong University (Science), 2013, 18(3): 334-342.