An Improved Gray Wolf Algorithm to Optimize LSSVR for Residual Life Prediction Method of Concrete Pump Truck Concrete Piston
-
摘要: 为了解决混凝土泵车砼活塞因无法及时更换导致设备停机的问题，提出一种改进灰狼算法优化最小二乘支持向量回归(LSSVR)的剩余寿命预测方法，该方法使用差分算法(DE)优化原始灰狼算法(GWO)，解决了其容易陷入局部最优解的问题，提高了收敛速度，使用优化后的算法优化最小二乘支持向量回归的两个参数，建立剩余寿命预测模型。通过真实的砼活塞寿命监测数据，使用3种评估指标对比LSSVR、GWO-LSSVR、DE-GWO-LSSVR这3个模型的预测效果，并与相关研究的结果进行对比。实验表明，DE-GWO-LSSVR模型拥有最高的预测精度，可以为砼活塞的预测性更换以及机械零件的故障诊断提供指导意义。
-
关键词:
- 砼活塞 /
- 差分进化 /
- 灰狼算法 /
- 最小二乘支持向量回归 /
- 剩余寿命预测
Abstract: In order to solve the problem that the concrete piston of the concrete pump truck could not be replaced in time,an improved gray wolf algorithm was proposed to optimized the remaining life prediction method of the Least Square Support Vector Regression (LSSVR).The new method DE-GWO-LSSVR uses the difference evolution algorithm to optimize the original gray wolf algorithm which solves the problem that it is easy to fall into the local optimal solution, improves the convergence speed, and then uses the optimized algorithm to optimize the two parameters of the least square support vector regression to establish the remaining life prediction model. Based on real concrete piston life monitoring data, three evaluation indicators are used to compare the prediction effects of the three models of LSSVR, GWO-LSSVR, and DE-GWO-LSSVR, and compare them with the results of related studies. Experiments show that the DE-GWO-LSSVR model has the highest prediction accuracy, which can provide guidance for the predictive replacement of concrete pistons and the fault diagnosis of mechanical parts. -
表 2 各模型预测误差指标
预测模型 MRE MAE MSE LSSVR 0.063 60.10 11 264.90 GWO-LSSVR 0.052 49.64 9 961.10 DE-GWO-LSSVR 0.047 44.83 8 373.15 
下载: 导出CSV
-
[1] 佘玲娟, 尹莉, 钟懿. 混凝土泵车高强钢臂架焊缝疲劳寿命预估[J]. 中国工程机械学报, 2019, 17(1): 29-33 doi: 10.15999/j.cnki.311926.2019.01.007SHE L J, YIN L, ZHONG Y. Fatigue life prediction of seam weld in the high strength steel boom structure of the concrete pump truck[J]. Chinese Journal of Construction Machinery, 2019, 17(1): 29-33 (in Chinese) doi: 10.15999/j.cnki.311926.2019.01.007 [2] 田相玉, 黄大为, 周志红. 基于有限元方法的混凝土泵车结构疲劳寿命预测[J]. 中国工程机械学报, 2017, 15(6): 542-546 + 551 doi: 10.15999/j.cnki.311926.2017.06.013TIAN X Y, HUANG D W, ZHOU Z H. Fatigue life prediction of concrete pump truck structure based on finite element method[J]. Chinese Journal of Construction Machinery, 2017, 15(6): 542-546 + 551 (in Chinese) doi: 10.15999/j.cnki.311926.2017.06.013 [3] WU Y Z, LI W J, LIU Y H. Fatigue life prediction for boom structure of concrete pump truck[J]. Engineering Failure Analysis, 2016, 60: 176-187 doi: 10.1016/j.engfailanal.2015.11.040 [4] 裴洪, 胡昌华, 司小胜, 等. 基于机器学习的设备剩余寿命预测方法综述[J]. 机械工程学报, 2019, 55(8): 1-13 doi: 10.3901/JME.2019.08.001PEI H, HU C H, SI X S, et al. Review of machine learning based remaining useful life prediction methods for equipment[J]. Journal of Mechanical Engineering, 2019, 55(8): 1-13 (in Chinese) doi: 10.3901/JME.2019.08.001 [5] 邱晓梅, 隋文涛, 王峰, 等. 基于相关系数和BP神经网络的轴承剩余寿命预测[J]. 组合机床与自动化加工技术, 2019(4): 63-65 doi: 10.13462/j.cnki.mmtamt.2019.04.015QIU X M, SUI W T, WANG F, et al. Remaining life prediction of bearing based on correlation coefficient and BP neural network[J]. Modular Machine Tool & Automatic Manufacturing Technique, 2019(4): 63-65 (in Chinese) doi: 10.13462/j.cnki.mmtamt.2019.04.015 [6] REN L, CUI J, SUN Y Q. Multi-bearing remaining useful life collaborative prediction: a deep learning approach[J]. Journal of Manufacturing Systems, 2017, 43: 248-256 doi: 10.1016/j.jmsy.2017.02.013 [7] 张继冬, 邹益胜, 邓佳林, 等. 基于全卷积层神经网络的轴承剩余寿命预测[J]. 中国机械工程, 2019, 30(18): 2231-2235ZHANG J D, ZOU Y S, DENG J L, et al. Bearing remaining life prediction based on full convolutional layer neural networks[J]. China Mechanical Engineering, 2019, 30(18): 2231-2235 (in Chinese) [8] 司春棣, 练继建, 郑杨. 土石坝渗流安全监测的遗传支持向量机方法[J]. 水利学报, 2007, 38(11): 1341-1346 doi: 10.3321/j.issn:0559-9350.2007.11.012SI C D, LIAN J J, ZHENG Y. Genetic support vector machine model for seepage safety monitoring of earth-rock dams[J]. Journal of Hydraulic Engineering, 2007, 38(11): 1341-1346 (in Chinese) doi: 10.3321/j.issn:0559-9350.2007.11.012 [9] 赵倩, 陈芳芳, 甘露. 基于改进粒子群算法优化支持向量机的风电功率预测[J]. 电气技术, 2020, 21(12): 12-16 doi: 10.3969/j.issn.1673-3800.2020.12.006ZHAO Q, CHEN F F, GAN L. Wind power prediction based on support vector machine trained by improved particle swarm optimization[J]. Electrical Engineering, 2020, 21(12): 12-16 (in Chinese) doi: 10.3969/j.issn.1673-3800.2020.12.006 [10] 张晓莉, 谢永成. 支持向量机参数优化方法在齿轮箱故障诊断中的应用[J]. 舰船电子工程, 2020, 40(9): 146-149 doi: 10.3969/j.issn.1672-9730.2020.09.035ZHANG X L, XIE Y C. Application of SVM parameter optimization method in gearbox fault diagnosis[J]. Ship Electronic Engineering, 2020, 40(9): 146-149 (in Chinese) doi: 10.3969/j.issn.1672-9730.2020.09.035 [11] SUYKENS J A K, VANDEWALLE J. Least squares support vector machine classifiers[J]. Neural Processing Letters, 1999, 9(3): 293-300 doi: 10.1023/A:1018628609742 [12] MIRJALILI S, MIRJALILI S M, LEWIS A. Grey wolf optimizer[J]. Advances in Engineering Software, 2014, 69: 46-61 doi: 10.1016/j.advengsoft.2013.12.007 [13] STORN R, PRICE K. Differential evolution – a simple and efficient heuristic for global optimization over continuous spaces[J]. Journal of Global Optimization, 1997, 11(4): 341-359 doi: 10.1023/A:1008202821328 [14] 金星, 邵珠超, 王盛慧. 一种基于差分进化和灰狼算法的混合优化算法[J]. 科学技术与工程, 2017, 17(16): 266-269 doi: 10.3969/j.issn.1671-1815.2017.16.043JIN X, SHAO Z C, WANG S H. A hybrid optimization algorithm based on differential evolution and grey wolf optimizer[J]. Science Technology and Engineering, 2017, 17(16): 266-269 (in Chinese) doi: 10.3969/j.issn.1671-1815.2017.16.043 [15] 刘杨成. 混凝土泵车砼活塞剩余寿命预测方法研究[J]. 现代制造工程, 2020(8): 120-125 doi: 10.16731/j.cnki.1671-3133.2020.08.019LIU Y C. Research on prediction method of remaining life of concrete piston in concrete pump truck[J]. Modern Manufacturing Engineering, 2020(8): 120-125 (in Chinese) doi: 10.16731/j.cnki.1671-3133.2020.08.019 -
点击查看大图
图(6) / 表(3)
计量
- 文章访问数: 172
- HTML全文浏览量: 86
- PDF下载量: 19
- 被引次数: 0
