Wear Trend Prediction of Crane Gearbox Based on OSVR Method with Combined Kernel Functions

Abstract

Abstract:

For the nonlinear and nonstationary crane gearbox wear process, prediction precision and efficiency cannot be effectively balanced by using traditional prediction methods. An OSVR prediction method based on combined kernel functions was proposed. The OSVR algorithm can be adapted to time-varying time series and the efficiency can be improved. Simultaneously, the kernel-combined model would be able to improve the prediction accuracy. Experimental results show that the trend of the crane gearbox wear process can be predicted effectively by using the new method, and the prediction is more accurate than the results of the OSVR method with single kernel function and the gray-neural network method.

Key words: gearbox, wear trend prediction;online support vector regression(OSVR), kernel function

摘要：

针对起重机减速齿轮箱的磨损过程具有非线性与时变性，传统磨损趋势预测方法无法有效兼顾预测精度与执行效率的问题，提出了一种基于组合核函数的在线支持向量机回归（online support vector regression，OSVR）预测算法。OSVR的在线学习算法能够适应时间序列的时变性并提高执行效率，同时可利用不同的核函数性能，通过组合模型提高预测精度。采用实际齿轮箱铁谱数据对预测算法进行验证，结果表明，基于组合核函数的OSVR预测算法具有很好的预测精度和适应性，能有效预测起重机齿轮箱的磨损故障，且相比于单一OSVR算法和灰色神经网络组合算法有更高的效率和预测精度。

关键词: 齿轮箱, 磨损趋势预测, 在线支持向量机回归, 核函数

CLC Number:

TP181

Cao Jinran, Feng Yi, Lu Baochun, Zhang Dengfeng, Wu Jian, Shi Shengzheng, Guan D. Wear Trend Prediction of Crane Gearbox Based on OSVR Method with Combined Kernel Functions[J]. China Mechanical Engineering, 2015, 26(5): 641-646.

曹劲然, 冯毅, 陆宝春, 张登峰, 吴建, 石胜征, 关德壮. 基于组合核函数OSVR算法的起重机减速齿轮箱磨损趋势预测[J]. 中国机械工程, 2015, 26(5): 641-646.

References

[1]时均莲,刘卓,乔新燃,等.海上平台起重机齿轮箱零部件失效形式分析及对策[J].起重运输机械,2012(7):73-76.
Shi Junlian,Liu Zhuo,Qiao Xinran,et al. Offshore Crane Gearbox Parts Failure Analysis and Countermeas-ures[J]. Hoisting and Conveying Machinery,2012(7):73-76.
[2]陈宏军,涂群章.基于油液分析的在线磨损监测技术研究现状与发展趋势[J]. 矿山机械,2008(24):22-25.
Chen Hongjun,Tu Qunzhang. Current Research and Development of the On-line Abrasion Monitoring Technique Based on Oil Analysis[J]. Mining & Processing Equipment, 2008(24):22-25.
[3]张菊,钟新辉,张峰.灰色系统在发动机铁谱分析监测中的应用[J].内燃机,2013(3):39-40,53.
Zhang Ju,Zhong Xinhui,Zhang Feng.Application of Gray System in Engine Ferrography Monitoring[J].Internal Combustion Engines, 2013(3):39-40,53.
[4]王金涛,吕晓军,谢友柏,等.在线铁谱监测系统中的非平稳磨损趋势分析[J].西安交通大学学报,2003,37(5):463-466.
Wang Jintao,Lü Xiaojun,Xie Youbai,et al. Nonstationary Wear Trend Analysis Method in On-Line Ferrograph Monitoring System[J]. Journal of Xi'an Jiaotong University,2003,37(5):463-466.
[5]陈果,杨虞微.航空发动机复杂磨损趋势的神经网络多变量预测模型[J].中国机械工程,2007,18(1):70-74.
Chen Guo，Yang Yuwei. Artificial Neural Network Multi-variable Forecasting Model of Aero-engine Complex Wear Trend[J]. China Mechanical Engineering, 2007,18(1):70-74.
[6]刘玉兵,陈亚忠,王晓东,等.BP神经网络修正灰色残差组合模型方法在油液光谱分析中应用的研究[J].润滑与密封,2007,32(3):172-174.
Liu Yubing，Chen Yazhong，Wang Xiaodong，et al. Research on Oil Spectral Analysis Prediction Based on Remnant Difference Correct Combined Model of BP Neural Network[J]. Lubrication Engineering, 2007, 32(3): 172-174.
[7]Debasish B，Srimanta P，Dipak C P.Support Vector Regression[J]. Neural Information Processing-Letters and Reviews, 2008, 11(10):203-224.
[8]刘大同,彭宇,彭喜元,等.基于残差预测修正的局部在线时间序列预测方法[J].电子学报,2008,36(12A):81-85.
Liu Datong，Peng Yu，Peng Xiyuan，et al. Local Online Time Series Prediction Based on the Residual Compensation with Online SVR[J]. Acta Electronica Sinica,2008,36(12A):81-85.
[9]Giovanni M，Francesco P.Learning to Trade with Incremental Support Vector Regression[J]. Lecture Notes in Computer Science, 2008,5271:591-598.
[10]Takens F.Detecting Strange Attractorin Turbulence[J]. Lecture Notes in Mathematics, 1981, 898(2): 361-381.
[11]张芬,陶亮,孙艳.基于混合核函数的SVM及其应用[J].计算机技术与发展,2006, 16(2):176-178.
Zhang Fen,Tao Liang,Sun Yan. SVM and Its Application Based on Mixtures of Kernels[J]. Computer Technology and Development, 2006, 16(2):176-178.
[12]王旭辉,黄圣国,曹力,等.基于LS-SVM的航空发动机气路参数趋势在线预测[J].吉林大学学报(工学版),2008,38(1):239-244.
Wang Xuhui，Huang Shengguo，Cao Li，et al. LS-SVM Based Online Trend Prediction of Gas Path Parameters of Aero Engine[J]. Journal of Jilin University(Engineering and Technology Edition),2008, 38(1):239-244.

[1]	KONG Shuai;CUI Hongyu;JI Shunying. Ice Load Identification Method of Ship Structures and Experimental Verification [J]. China Mechanical Engineering, 2020, 31(03): 281-288.
[2]	CHEN Xuefeng, GUO Yanjie, XU Caibin, SHANG Hongbing. Review of Fault Diagnosis and Health Monitoring for Wind Power Equipment [J]. China Mechanical Engineering, 2020, 31(02): 175-189.
[3]	JIN Qi, WANG Youren, WANG Jun. Planetary Gearbox Fault Diagnosis Based on Multiple Feature Extraction and Information Fusion Combined with Deep Learning [J]. China Mechanical Engineering, 2019, 30(02): 196-204.
[4]	WANG Youren;WANG Jun;HUANG Haian. Fault Diagnosis of Planetary Gearboxes Based on NLSTFT Order Tracking under Variable Speed Conditions [J]. China Mechanical Engineering, 2018, 29(14): 1688-1695.
[5]	YU Jun1，2;YU Deshui1. Applications of Flow Graph to Fault Diagnosis of Planetary Gearboxes [J]. China Mechanical Engineering, 2018, 29(10): 1208-1213.
[6]	JIA Ziwen;GU Yujiong. Wind Turbine Gearbox Operation State Analysis Based on Data Mining [J]. China Mechanical Engineering, 2018, 29(06): 650-658.
[7]	WANG Xuan1,2;WANG Xiyang1. Measurement and Analysis of Torsional Vibration Signals for Diagnosing Planetary Gearbox Faults [J]. China Mechanical Engineering, 2018, 29(01): 49-56.
[8]	HE Qun1;GUO Yuangeng1;WANG Xiao1,2;REN Zonghao1;LI Jimeng1. Gearbox Fault Diagnosis Based on RB-SSD and MCKD [J]. China Mechanical Engineering, 2017, 28(13): 1528-1534.
[9]	WANG Youren, CHEN Wei, SUN Canfei, SUN Quan, HUANG Haian. Early Weak Fault Diagnosis of Gearboxes Based on Energy Aggregation and EWT [J]. China Mechanical Engineering, 2017, 28(12): 1484-1490.
[10]	YANG Yu, LUO Peng, CHENG Junsheng. GVMD and Its Applications in Composite Fault Diagnosis for Gearboxes [J]. China Mechanical Engineering, 2017, 28(09): 1069-1073.
[11]	Gu Yingkui, Pan Gaoping, Zhu Fanlong, Cheng Zixin. Gearbox Fault Feature Reduction Based on Neighborhood Attribute Importance and PCA [J]. China Mechanical Engineering, 2016, 27(13): 1783-1789.
[12]	Han Jiang, Wu Lulu, Tian Xiaoqing, Xia Lian. Synchronous Coupling Control Method of Electronic Gearbox [J]. China Mechanical Engineering, 2016, 27(07): 877-881,887.
[13]	Yang Changhui, Xu Taojin, Wu Canyuan. Analyses of Dynamic Coupling Characteristics and Structural Noise of Multi-Megawatt Wind Turbine Gearbox [J]. China Mechanical Engineering, 2016, 27(05): 609-614,621.
[14]	Yang Yu, Li Yongguo, He Zhiyi, Cheng Junsheng. BSS Method of Gearbox Multi-fault Based on LCD [J]. China Mechanical Engineering, 2015, 26(8): 1062-1066.
[15]	Tian Xiaoqing , Han Jiang, Xia Lian . Precision Control and Experiments of Electronic Gearbox [J]. China Mechanical Engineering, 2015, 26(2): 211-216.