Identification of Reliability Life Distribution of Hydraulic Pump Based on KPCA and FSVM

Abstract

Abstract:

Aiming at identifying the reliability life distribution model of the hydraulic pump accurately and efficiently, an algorithm of KPCA and FSVM was brought forward. The recognition model of the reliability life distribution model was designed by making full use of advantages of the KPCA nonlinear feature extraction and the FSVM classification capacity, and might be used for identifying the reliability life distribution model of the hydraulic pump. The simulation results show that, the proposed method can reduce computation complexity, has good ability for generalization, and identify the life distribution type of life on time between failures of hydraulic pump accurately.

Key words: kernel principal component analysis（KPCA）, fuzzy support vector machine（FSVM）, life distribution model, hydraulic pump, time between failures

摘要：

为了准确快速识别出液压泵的可靠性寿命分布模型，提出了一种基于核主元分析和模糊支持向量机的可靠性寿命分布模型识别方法。该方法充分利用核主元分析非线性特征提取的优势和模糊支持向量机良好的分类能力，建立了适合可靠性寿命分布识别的模糊支持向量机模型，并将其应用于液压泵可靠性寿命分布模型识别。仿真实验结果表明，该模型能够降低计算的复杂度，具有良好的泛化能力，能够准确地识别出液压泵无故障工作时间数据所属的寿命分布类型。

关键词: 核主元分析, 模糊支持向量机, 寿命分布模型, 液压泵, 无故障工作时间

CLC Number:

Jing Tao, Cao Keqiang, Hu Liangmou, Gao Bin. Identification of Reliability Life Distribution of Hydraulic Pump Based on KPCA and FSVM[J]. China Mechanical Engineering, 2015, 26(19): 2595-2600.

景涛, 曹克强, 胡良谋, 高斌. 基于KPCA-FSVM的液压泵可靠性寿命分布识别[J]. 中国机械工程, 2015, 26(19): 2595-2600.

References

[1]沈燕良.飞机系统原理[M]. 北京：国防工业出版社，2010.
[2]何庆飞，陈桂明，陈小虎，等. 基于灰色支持向量机的液压泵寿命预测方法[J]. 润滑与密封，2012，37(4)：75-77.
He Qingfei, Chen Guiming, Chen Xiaohu, et al. Life Prediction Method of Hydraulic Pump Based on Grey Support Vector Machines[J]. Lubrication Engineering, 2012，37(4)：75-77.
[3]朱家元，张恒喜，田松，等. 基于复合神经网络的数据分布模式仿真识别[J]. 系统工程与电子技术，2002，24（10）:96-99.
Zhu Jiayuan, Zhang Hengxi, Tian Song, et al. Data Distribution Simulation Identification Using Combined Structure Neural Networks[J]. Systems Engineering and Electronics，2002，24（10）:96-99.
[4]朱家元，张恒喜，张喜斌. 基于智能复合结构的可靠性分布模式自动识别[J]. 航空学报，2003，24（3）：207-211.
Zhu Jiayuan, Zhang Hengxi, Zhang Xibin. Reliability Distributions Automatic Identification Based on Intelligent Combined Structure Model[J]. Journal of Aviation， 2003，24（3）：207-211.
[5]韩强，祝华远，孙明礼，等. 基于支持向量机的小样本数据概率分布模式自动识别[J]. 科学技术与工程，2009，9（10）：2766-2769.
Han Qiang, Zhu Huayuan, Sun Mingli, et al. Modeling Distributions Identification for Small Samples Based on SVM[J]. Science Technology and Engineering, 2009，9（10）：2766-2769.
[6]郝惠敏, 汤晓君, 白鹏, 等. 基于核主成分分析和支持向量回归机的红外光谱多组分混合气体定量分析[J]. 光谱学与光谱分析，2008，28（6）：1286-1289.
Hao Huimin, Tang Xiaojun, Bai Peng, et al. Quantitative Analysis of Multi-component Gas Mixture Based on KPCA and SVR[J]. Spectroscopy and Spectral Analysis, 2008，28（6）：1286-1289.
[7]彭涛，杨慧斌，李建宝，等. 基于核主元分析的滚动轴承故障混合域特征提取方法[J]. 中南大学学报（自然科学版），2011，42（11）：3385-3391.
Peng Tao，Yang Huibin，Li Jianbao，et al. Mixed—domain Feature Extraction Approach to Rolling Bearings Faults Based on Kernel Principle Component Analysis[J]. Journal of Central South University(Science and Technology), 2011，42（11）：3385-3391.
[8]宋平，文妍，谭继文. KPCA和遗传BP神经网络在滚珠丝杠故障诊断中的应用研究[J]. 机床与液压，2014，42（9）：159-162.
Song Ping，Wen Yan，Tan Jiwen. Application Research of KPCA and GA-BP Network in Ball Screw Fault Diagnosis[J]. Machine Tool ＆ Hydraulic，2014，42（9）：159-162.
[9]周欣，吴瑛. 基于KPCA和LDA的信号调制识别[J]. 系统工程与电子技术，2011，33（7）:1611-1616.
Zhou Xin, Wu Ying. Signal Modulation Recognition Based on KPCA and LDA[J]. Systems Engineering and Electronics, 2011，33（7）:1611-1616.
[10]张曦，阎威武，刘振亚，等. 基于核主元分析和邻近支持向量机的汽轮机凝汽器过程监控和故障诊断[J]. 中国电机工程学报，2007，27（14）：56-61.
Zhang Xi，Yan Weiwu，Liu Zhenya，et al. Process Monitoring and Fault Diagnosis of Condenser Using KPCA and PSVM[J]. Proceeding of the CSEE, 2007，27（14）：56-61.
[11]Scholkopf B, Smola A, Muller K-R. Nonlinear Component Analysis as a Kernel Eigenvalue Problem[J]. Neural Computation, 1998，10(5)：1299-1319．
[12]陈家德，吴小俊. 自适应模糊支持向量机算法研究[J]. 计算机工程与应用，2010，46（25）: 191-194.
Chen Jiade，Wu Xiaojun. Study on Adaptive Fuzzy Support Vector Machine Algorithm[J]. Computer Engineering and Applications, 2010，46（25）: 191-194.
[13]Inoue T, Abe S. Fuzzy Support Vector Machines for Pattern Classification[C]//International Joint Conference on Neural Networks. Killarney，Ireland，2001：1449-1454.
[14]吴月明，王毅群，李莉. BP神经网络与广义RBF神经网络在产品寿命分布模型识别中的应用研究[J]. 中国机械工程，2006，17（20）：2140-2143.
Wu Yueming, Wang Yiqun, Li Li. Application Study on BP Network and Generalized RBF Network in Estimating Distribution Model of Mechanical Products[J]. China Mechanical Engineering, 2006，17（20）：2140-2143.

[1]	SHAN Zenghai, LI Zhiyuan, ZHANG Xu, HUANG Yixiang, LI Yanming, LIU Chengliang, ZHANG Xuan. Health Status Assessment of Hydraulic Pumps Based on Multi-sensor Information Fusion and Multi-grained Cascade Forest Model [J]. China Mechanical Engineering, 2021, 32(19): 2374-2382.
[2]	LIU Siyuan1,2;WANG Guangda1,2;SUN Hongmei3;LIU Jianxun4;JIANG Wanlu1,2. Prediction Method of Performance of Intelligent Hydraulic Components Based on Lubrication Mechanism [J]. China Mechanical Engineering, 2020, 31(08): 952-959.
[3]	LIU Siyuan1，2，3;HE Yue1，2;LI Xiaoming4;LU Mingli3;LU Zhengdian3. Multi-information Intensity Characteristic State Assessment Method of Hydraulic Pums Based on Fault Mechanism [J]. China Mechanical Engineering, 2019, 30(12): 1460-1465,1473.
[4]	ZHOU Yuwei;ZHANG Qing;SHI Yunfei. Simulation and Verification of Hydraulic Control Systems for Continuous Lifting [J]. China Mechanical Engineering, 2018, 29(16): 1936-1942.
[5]	YU Yaxin1;JIANG Jianyu1;JIN Bo2,3;CHEN Xing2;FENG Yixiong2,3. Flow Characteristics of Spherical Blade Hydraulic Pumps [J]. China Mechanical Engineering, 2018, 29(08): 930-936.
[6]	ZHAO Chunhua, WANG Chengkang, HUA Lu, ZHENG Siyu, LIANG Zhipeng. Control Chart Pattern Recognition Based on Fusion Feature Reduction and SVM [J]. China Mechanical Engineering, 2017, 28(08): 930-935.
[7]	Liu Zhiqiang, Jiang Wanlu, Tan Wenzhen, Zhu Yong, . Fault Identification Method for Hydraulic Pumps Based on Multi-feature Fusion and Multiple Kernel Learning SVM [J]. China Mechanical Engineering, 2016, 27(24): 3355-3361.
[8]	Liu Siyuan, Yang Mengxue, Wang Chuang, Zhang Wenwen. Morphological Filtering Method for Vibration Signals of Hydraulic Pump under Sinusoidal Variable Load Conditions [J]. China Mechanical Engineering, 2016, 27(19): 2557-2563.
[9]	Wang Yukui, Li Hongru, Ye Peng. Fault Identification of Hydraulic Pump Based on Multi-scale Permutation Entropy [J]. China Mechanical Engineering, 2015, 26(4): 518-523.
[10]	Wang Yukui, Li Hongru, Xu Baohua. Fault Pattern Identification of Hydraulic Pump Based on VPMCD and LPP Algorithm [J]. China Mechanical Engineering, 2015, 26(24): 3327-3335.
[11]	HE Qiang-Fei, CHEN Gui-Meng, CHEN Xiao-Hu, TAO Chun-Jiang. Life Prediction of Hydraulic Pump Based on an Improved Grey Neural Network [J]. China Mechanical Engineering, 2013, 24(4): 500-506.
[12]	TIAN Hai-Lei, LI Hong-Ru, HU Bao-Hua. Prediction for Pressure Signals of Hydraulic Pump Based on Wavelet Packet-chaos Theory and SVM [J]. China Mechanical Engineering, 2013, 24(08): 1085-1089.
[13]	TIAN Hai-Lei, LI Hong-Ru, HU Bao-Hua. Fault Prediction for Hydraulic Pump Based on EEMD and SVM [J]. China Mechanical Engineering, 2013, 24(07): 926-931.
[14]	HUANG Guo-Qi-1, HE Xiao-Feng-2, SHU Yu-Quan-2. Analysis on Optimal Clearance of Piston Friction Pair and Its Influence Factors for Water Hydraulic Pump [J]. China Mechanical Engineering, 2011, 22(14): 1668-1672.
[15]	Liu Tao,;Jiang Jihai;Sun Hui. Research on Regenerative Braking Control Strategy for  Parallel Hydraulic Hybrid Vehicles Based on Backward Modeling [J]. J4, 2009, 20(15): 0-1770.