A study on optimization of the LSSVM model for crane load spectrum regression prediction

PDF(4036 KB)

Journal of Vibration and Shock ›› 2022, Vol. 41 ›› Issue (12) : 215-228.

YU Yannan,QI Qisong,DONG Qing,XU Gening

Author information +

History +

Abstract

Accurately obtaining the load spectrum of an in-service crane under normal working conditions is a necessary condition for predicting and evaluating the fatigue remaining life of the crane. However, due to the uncertainty, diversity, and randomness of the crane load, and the complexity of the actual measurement environment on site, it is still very difficult to assess the fatigue life of cranes. In order to solve the problem of low accuracy and small sample size of crane load spectrum prediction, based on optimization algorithm and machine learning technology, an improved beetle antennae search algorithm was proposed to optimize the regression prediction model of least square support vector machine(LSSVM), and the IBAS-LSSVM model is established. Based on the traditional beetle antennae search algorithm, the update of the step size is controlled by the inverse tangent function, and the method that can jump out of the algorithm stagnation is set, so as to avoid the algorithm from falling into the local optimum, the global optimization performance of the algorithm is improved. A certain type of general bridge crane is taken as an example. The IBAS-LSSVM model is used to perform regression prediction and analysis on the small sample load spectrum of the crane. The results show that compared with other regression prediction models, the IBAS-LSSVM prediction model proposed has more high prediction accuracy, faster convergence speed and better generalization performance. In addition, it avoids the problem of falling into local minimums. This method is of great significance for the regression prediction of crane load spectrum and the evaluation of crane fatigue remaining life.

Key words

crane / load spectrum / beetle antennae search algorithm / least square support vector machine(LSSVM)

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

YU Yannan,QI Qisong,DONG Qing,XU Gening. A study on optimization of the LSSVM model for crane load spectrum regression prediction[J]. Journal of Vibration and Shock, 2022, 41(12): 215-228

References

[1] 王爱红,徐格宁,高有山.桥式起重机随机应力谱获取及疲劳剩余寿命估算[J].机械工程学报,2012,48(18):192-198.
WANG Ai-hong, XU Ge-ning， GAO You-shan. Random Stress Spectrum Acquisition and Fatigue Residual Life Estimate for Overhead Travelling Crane [J]. Journal of Mechanical Engineering，2012,48(18):192-198.
[2] 王鑫,孙同峰,郭富城.桥式起重机载荷应力谱分析与优化[J].中国新技术新产品,2019(01):52-53.
Wang Xin, Sun Tong-feng, Guo Fu-cheng. Analysis and optimization of load stress spectrum of bridge crane [J]. China New Technology and New Products,2019(01):52-53.
[3] 李国勇.智能控制及其MATLAB实现[M].北京:电子工业出版社,2005．
[4] 徐秉铮,张百灵,韦刚.神网络理论与应用[M].广州:大学出版社,1994.
[5] Vapnilk V, Golwich S, Smola A J. Support vector method for function approximation, regression estimation and signal processing. [J]. Advances in Neural Information Processing Sys-tems, 1997, 281-287.
[6] Tipping M E. Sparse bayesian learning and the relevancevector machine [J]. Journal of Machine Leaming Research,2001,1:211-244.
[7] Bishop C M, Tipping M E. variational relevance vector machines[J]. Computer Science, 2013,28:46-53.
[8] 陆凤仪,王爽,徐格宁,等.构建起重机载荷谱v-SVRM预测模型的改进方法[J].工程设计学报,2015,22(05):412-419.
LU Feng-yi, WANG Shuang, XU Ge-ning,et al．Improved modeling method for prediction model of crane load spectrum based on support vector regression machine[J]. Chinese Journal of Engineering Design,2015,22(05):412-419.
[9] 徐格宁,张魏唯,董青, 等. 基于粒子群优化相关向量机的起重机当量载荷谱预测方法[J].机械设计与研究,2018,34(01):188-193+198.
XU Ge-ning, ZHANG Wei-wei，DONG Qing,et al. Equivalent load spectrum prediction method of crane based on relevance vector machine optimized by particle swarm optimization [J]. Machine Design and Research, 2018,34(01):188-193+198.
[10] 董青,徐格宁.自适应双层果蝇相关向量机起重机当量载荷谱预测方法[J].机械设计,2017,34(02):86-93.
DONG Qing，XU Ge-ning. Crane equivalent load spectrum prediction method based on relevance vector machine improved by adaptive double layer fruit fly algorithm. [J]. Journal of Machine Design, 2017,34(02):86-93.
[11] 张小龙, 张氢, 秦仙蓉,等. 基于ITD复杂度和PSO-SVM的滚动轴承故障诊断[J]. 振动与冲击, 2016, 35(24): 102-107.
ZHANG Xiaolong,ZHANG Qing,QIN Xianrong,et al.Rolling bearing fault diagnosis based on ITD Lempel-Ziv complexity and PSO-SVM [J].Journal of Vibration and Shock, 2016, 35(24): 102-107.
[12] 刘伯颖,胡佳程,李玲玲,等.IGBT老化状态下基于BAS-SVM模型的结温预测方法[J].微电子学,2020,50(05):664-668+682.
LIU Bo-ying, HU Jia-cheng, LI Ling-ling, et al. Junction temperature prediction method based on BAS-SVM model in aging state of IGBT[J]. Microelectronics, 2020,50(05):664-668+682.
[13] 王雪莹,张君婷,赵全明.基于改进鸟群算法优化最小二乘支持向量机的锂离子电池寿命预测方法研究[J].电气应用,2020,39(07):74-78.
WANG Xue-ying, ZHANG Jun-ting, ZHAO Quan-ming. Research on lithium-ion battery life prediction method based on improved fock algorithm least squares support vector machine. [J]. Electrical application,2020,39(07):74-78.
[14] 张永康, 李春祥, 郑晓芬,等.基于混合人工蜂群和人工鱼群优化的LSSVM脉动风速预测[J].振动与冲击,2017, 36(015):203-209.
ZHANG Yongkang, LI Chunxiang, ZHENG Xiaofen,et al. Fluctuating wind velocity prediction using LSSVM based on hybrid intelligent optimization of ABC and ABF [J].Journal of Vibration and Shock, 2017, 36(015):203-209.
[15] 温静媛,苗鸿宾,刘晓峰. 基于BAS-BP的深孔加工粗糙度的预测[J].机械设计与研究, 2019,35(05):80-83.
WEN Jing-yuan , MIAO Hong-binl, LIU Xiao-feng. Roughness prediction in deep hole based on BAS-BP. [J]. Machine Design and Research, 2019,35(05):80-83.
[16] 许景辉,刘政光,周宇博.基于IBAS-BP算法的冬小麦根系含水率预测模型研究[J].农业机械学报,2021,52(02):294-299.
Xu Jing-hui,Liu Zheng-guang Zhou Yu-bo. Prediction of root water content of winter wheat based on IBAS-BP model[J]. Transactions of the Chinese Society for Agricultural Machinery , 2021,52(02):294-299.
[17] 闫重熙,陈皓.基于改进天牛须搜索算法优化LSSVM短期电力负荷预测方法研究[J].电测与仪表,2020,57(06):6-11+18.
Yan Chong-xi, Chen Hao. Research of LSSVM short-term load forecasting method based on the improved beetle antennae search algorithm. [J]. Electrical Measurement & Instrumentation,2020,57(06):6-11+18.
[18] Lin G Q , Li L L , Tseng M L , et al. An improved moth-flame optimization algorithm for support vector machine prediction of photovoltaic power generation[J]. Journal of Cleaner Production, 2020, 253:119966.
[19] Li L L, Cen Z Y, Tseng M L, et al. Improving short-term wind power prediction using hybrid improved cuckoo search arithmetic Support vector regression machine, [J]. Journal of Cleaner Production, 2021, 279:123739.
[20] Helaleh A H , Alizadeh M . Performance prediction model of miscible surfactant-CO2 displacement in porous media using support vector machine regression with parameters selected by ant colony optimization[J]. Journal of Natural Gas Science & Engineering, 2016:388-404.
[21] Rui J , Zhang H , Zhang D , et al. Total organic carbon content prediction based on support-vector-regression machine with particle swarm optimization[J]. Journal of Petroleum Science and Engineering, 2019, 180:699-706.
[22] 陈法法, 刘莉莉, 刘芙蓉,等. 归一化小波熵与RVM的滚动轴承运行可靠度预测[J]. 振动与冲击,2020, 364(08):13-19
CHEN Fafa , LIU Lili, LIU Furong,et al. Roller bearing operation reliability prediction based on Relevance Vector Machine and normalized wavelet decomposition information entropy [J]. Journal of Vibration and Shock, 2020, 364(08):13-19
[23] 冯鹏飞, 朱永生, 王培功，等.基于相关向量机模型的设备运行可靠性预测[J].振动与冲击,2017, 12(296):151-154+185.
FENG Pengfei, ZHU Yongsheng, WANG Peigong, et al. Operational reliability prediction of equipment based on relevance vector machine [J].Journal of Vibration and Shock, 2017, 12(296):151-154+185.
[24] Xu Y,Huang Y M,Ma G W. A beetle antennae search improved BP neural network model for predicting multi-factor-based gas explosion pressures, [J]. Journal of Loss Prevention in the Process Industries, 2020,65:104117.
[25] Xing B, Gao W J. Fruit fly optimization algorithm [M]. Berlin: Springer Intermational Publishing, 2014: 167-170.
[26] Seyedali M. Andrew L. The whale optimization algorithm [J]. Engineering Software, 2016, 95(5): 51-67.
[27] 汪定伟,王俊伟,王洪峰等.智能优化方法[M].北京:高等教育出版社,2007.
[28] Holland J H. Adaptation in natural and artificial systems [J]. Ann Arbor, 1992,6 (2) :126-137.
[29] Cortes C, Vapnik V. Support-vector networks. [J] Machine Learning, 1995, 20: 273–297
[30] Vapnik V. Statistical Learning Theory. New York: John Wiley & Sons, 1998
[31] SUYKENS JAK, VANDEWALLE J. Least squares support vector machine classifiers [J]. Neural Processing, 1999, 9(3):293-300.
[32] Jiang X, Li S. BAS: beetle antennae search algorithm for optimization problems [J]. International Journal of Robotics & Control, 2018, 1(1): 1-5.
[33] 赵玉强,钱谦,周田江,等.天牛须搜索与遗传的混合算法[J].小型微型计算机系统,2020,41(07):1438-1445.
ZHAO Yu-qiang, QIAN Qian, ZHOU Tian-jiang. Hybrid optimization algorithm based on beetle antennae search and genetic evolution[J]. Journal of Chinese Computer Systems, ,2020,41(07):1438-1445.
[34] 于嘉鹏,袁鹤翔,杨永华,等.基于自适应天牛须算法的航空发动机管路布局优化[J].机械工程学报,2020,56(20):174-184.
YU Jia-peng, YUAN He-xiang, YANG Yong-hua, et al. Aero-engine pipe layout optimization based on adaptive beetle antennae search algorithm[J]. Journal of Mechanical Engineering,2020,56(20):174-184.