基于PSO-SVR的海缆刚度预测模型研究

苏凯; 赵鑫蕊; 朱洪泽; 程永光

doi:10.19912/j.0254-0096.tynxb.2023-0505

PDF(1111 KB)

太阳能学报 ›› 2024, Vol. 45 ›› Issue (8) : 458-465. DOI: 10.19912/j.0254-0096.tynxb.2023-0505

基于PSO-SVR的海缆刚度预测模型研究

苏凯, 赵鑫蕊, 朱洪泽, 程永光

作者信息 +

STUDY ON PREDICTION MODEL OF SUBMARINE CABLE STIFFNESS BASED ON PSO-SVR ALGORITHM

Su Kai, Zhao Xinrui, Zhu Hongze, Cheng Yongguang

Author information +

文章历史 +

摘要

海缆刚度是表征海缆截面力学特性的重要指标。精细数值模拟方法可考虑层间接触、摩擦等非线性行为,实现刚度的精确获取。但在海缆的截面初步设计中需进行不同几何参数下刚度的对比分析,这一过程需投入大量的人力物力以完成多个对比模型的建模与计算。依托Nysted海上风电工程,建立海缆的有限元模型,采用正交试验法确定影响海缆抗拉刚度、逆时针抗扭刚度和顺时针抗扭刚度的主要因素;将主要影响因素作为粒子群优化算法-支持向量回归模型（PSO-SVR）的特征输入,分别建立海缆抗拉刚度、逆时针抗扭刚度和顺时针抗扭刚度的预测模型,并对比分析PSO-SVR模型与GRNN神经网络模型、BP神经网络模型的预测性能。计算结果表明：导体直径、钢丝直径、钢丝节距和铠装层数对海缆刚度的影响较大,而钢丝弹模对其影响较小;PSO-SVR模型的决定系数高于0.95且误差较低,预测效果均优于GRNN神经网络模型和BP神经网络模型,该预测模型可为海缆结构初步设计提供技术支撑。

Abstract

Submarine cable stiffness is an important index to characterize the cross-sectional mechanical properties. Fine numerical simulation methods can consider nonlinear behaviors such as interlayer contact and friction to obtain the exact stiffness. However, in the preliminary design of the submarine cable cross-section, it is necessary to conduct a comparative analysis of the stiffness under different geometric parameters, which requires a significant amount of manpower and material resources to complete the modeling and calculation of multiple comparative models. This study establishes a finite element model of the submarine cable based on the Nysted offshore wind farm project, and uses the orthogonal test method to determine the main factors influencing the tensile stiffness, counterclockwise torsional stiffness and clockwise torsional stiffness of the submarine cable. Then, the main influencing factors are used as feature inputs of the Particle Swarm Optimization-Support Vector Regression （PSO-SVR） model to establish prediction models for tensile stiffness, counterclockwise torsional stiffness and clockwise torsional stiffness of the submarine cable respectively. Besides, the prediction performance of the PSO-SVR model is compared with the GRNN neural network model and the BP neural network model. The results show that the conductor diameter, steel wire diameter, steel wire pitch and the number of armor layers have more influence on the submarine cable stiffness, while the steel wire elastic modulus has less influence on it. The determination coefficient of the PSO-SVR model is higher than 0.95 and the error is relatively low, and the prediction performance is better than that of the GRNN neural network model and the BP neural network model. This prediction model can provide technical support for the preliminary design of submarine cable structures.

导出引用

苏凯, 赵鑫蕊, 朱洪泽, 程永光. 基于PSO-SVR的海缆刚度预测模型研究[J]. 太阳能学报. 2024, 45(8): 458-465 https://doi.org/10.19912/j.0254-0096.tynxb.2023-0505

Su Kai, Zhao Xinrui, Zhu Hongze, Cheng Yongguang. STUDY ON PREDICTION MODEL OF SUBMARINE CABLE STIFFNESS BASED ON PSO-SVR ALGORITHM[J]. Acta Energiae Solaris Sinica. 2024, 45(8): 458-465 https://doi.org/10.19912/j.0254-0096.tynxb.2023-0505

中图分类号： P751

参考文献

[1] HRUSKA F H.Calculation of stresses in wire ropes[J]. Wire wire prod, 1951, 26(9): 799-801.
[2] KNAPP R H.Derivation of a new stiffness matrix for helically armoured cables considering tension and torsion[J]. International journal for numerical methods in engineering, 1979, 14(4): 515-529.
[3] WITZ J A, TAN Z.On the axial-torsional structural behaviour of flexible pipes, umbilicals and marine cables[J]. Marine structures, 1992, 5(2-3): 205-227.
[4] LOVE A E H. A treatise on the mathematical theory of elasticity[M]. 4th edition. Cambridge: University Press, 1927.
[5] CHANG H C, CHEN B F.Mechanical behavior of submarine cable under coupled tension, torsion and compressive loads[J]. Ocean engineering, 2019, 189: 106272.
[6] KAGOURA T, ISHII K I, ABE S, et al.Development of a flexible pipe for pipe-in-pipe technology[J]. Furukawa review, 2003, 24: 69-75.
[7] VAZ M A, AGUIAR L, ESTEFEN S F, et al.Experimental determination of axial, torsional and bending stiffness of umbilical cables[C]//Proceedings of the 17th International Offshore & Arctic Engineering Conference. Lisbon, Portygal, 1998.
[8] 肖能. 水下生产系统脐带缆截面设计与分析[D]. 大连: 大连理工大学, 2011.
XIAO N.Cross-section design and analysis of umbilical cable in subsea production system[D]. Dalian: Dalian University of Technology, 2011.
[9] FANG P, JIANG X L, HOPMAN H, et al.Mechanical responses of submarine power cables subject to axisymmetric loadings[J]. Ocean engineering, 2021, 239: 109847.
[10] 张克超, 郭海燕, 赵伟, 等. 海洋脐带缆截面力学性能分析与数值模拟[J]. 中国海洋大学学报, 2019, 49(增刊1): 128-134.
ZHANG K C, GUO H Y, ZHAO W, et al.Sectional mechanical properties analysis and numerical simulation of marine umbilical cable[J]. Periodical of Ocean University of China, 2019, 49(S1): 128-134.
[11] 张宇. 隧道工程围岩变形预测的人工智能方法及集成[D]. 北京: 北京交通大学, 2009.
ZHANG Y.Artificial intelligence method and integration of surrounding rock deformation prediction in tunnel engineering[D]. Beijing: Beijing Jiaotong University, 2009.
[12] 伍鹤皋, 于金弘, 石长征, 等. 基于正交试验法的埋地钢管参数敏感性分析[J]. 长江科学院院报, 2021, 38(8): 97-103.
WU H G, YU J H, SHI C Z, et al.Sensitivity analysis for parameters of buried steel pipes based on orthogonal test method[J]. Journal of Yangtze River Scientific Research Institute, 2021, 38(8): 97-103.
[13] 邰淑彩, 孙韫玉, 何娟娟. 应用数理统计[M]. 武汉: 武汉大学出版社, 2005.
TAI S C, SUN Y Y, HE J J.Applied mathematical statistics[M]. Wuhan: Wuhan University Press, 2005.
[14] VAPNIK V N.The nature of statistical learning theory[M]. New York: Springer New York, 1995.
[15] 张伟, 林莉, 樊俊铃, 等. 基于PSO-SVR的非均质涂层组织均匀性超声表征[J]. 中国表面工程, 2022, 35(6): 222-231.
ZHANG W, LIN L, FAN J L, et al.Ultrasonic quantitative characterization of heterogeneous coating microstructure uniformity based on PSO-SVR[J]. China surface engineering, 2022, 35(6): 222-231.
[16] 宋威, 刘开云, 梁军平, 等. 基于免疫多输出支持向量回归算法的隧道工程位移反分析新方法[J]. 铁道学报, 2022, 44(2): 126-134.
SONG W, LIU K Y, LIANG J P, et al.New method for back analysis of tunnel displacement based on immune multiple output support vector regression algorithm[J]. Journal of the China Railway Society, 2022, 44(2): 126-134.
[17] 张振全, 李醒飞, 杨少波. 基于AR-SVR模型的有效波高短期预测[J]. 太阳能学报, 2021, 42(7): 15-20.
ZHANG Z Q, LI X F, YANG S B.Short-term prediction of significant wave height based on ar-svr model[J]. Acta energiae solaris sinica, 2021, 42(7): 15-20.
[18] 冯建英, 贺苗, 李鑫, 等. 基于改进MSVR的鲜食葡萄运输过程中环境因子与感官品质建模[J]. 农业工程学报, 2022, 38(17): 294-302.
FENG J Y, HE M, LI X, et al.Modeling of environmental factors and sensory quality during transportation of table grapes using improved MSVR[J]. Transactions of the Chinese Society of Agricultural Engineering, 2022, 38(17): 294-302.
[19] 吴奇, 严洪森. 基于具有高斯损失函数支持向量机的预测模型[J]. 计算机集成制造系统, 2009, 15(2): 306-312, 332.
WU Q, YAN H S.Forecasting method based on support vector machine with Gaussian loss function[J]. Computer integrated manufacturing systems, 2009, 15(2): 306-312, 332.
[20] 周婷, 金菊良, 李荣波, 等. 基于小波支持向量机的径流预测性能优化分析[J]. 水力发电学报, 2017, 36(10): 45-55.
ZHOU T, JIN J L, LI R B, et al.Performance optimization analysis for inflow prediction using wavelet support vector machine[J]. Journal of hydroelectric engineering, 2017, 36(10): 45-55.
[21] 黄宝洲, 杨俊华, 卢思灵, 等. 基于改进粒子群优化神经网络算法的波浪捕获功率预测[J]. 太阳能学报, 2021, 42(2): 302-308.
HUANG B Z, YANG J H, LU S L, et al.Wave capture power forecasting based on improved particle swarm optimization neural network algorithm[J]. Acta energiae solaris sinica, 2021, 42(2): 302-308.
[22] BADRAN E A, RIZK M E, ABDEL-RAHMAN M H. Investigation of submarine cable parameters impact on energization transients in offshore wind farms[C]//International Conference on Power Systems Transients.IPST, Delft, The Netherlands, 2011.
[23] 陆钰天. 深水柔性立管截面力学模型与疲劳寿命分析研究[D]. 杭州: 浙江大学, 2017.
LU Y T.Study on mechanical model and fatigue life analysis of deep water flexible riser section[D]. Hangzhou: Zhejiang University, 2017.
[24] 陈大勇, 张慧甍, 董小松, 等. 海底电缆抗拉性能数值分析[J]. 电线电缆, 2021(4): 19-22.
CHEN D Y, ZHANG H M, DONG X S, et al.Numerical analysis of tensile properties of submarine cables[J]. Wire & cable, 2021(4): 19-22.
[25] 国家质量监督检验检疫总局, 中国国家标准化管理委员会. 电缆的导体: GB/T 3956—2008[S]. 北京: 中国标准出版社, 2009.
General Administration of Quality Supervision, Inspection and Quarantine of the People’s Republic of China, Standardization Administration of the People’s Republic of China. Conductors of insulated cables: GB/T 3956—2008[S]. Beijing: Standards Press of China, 2009.
[26] 龚永超, 何旭涛, 孙建生, 等. 高压海底电力电缆铠装的设计和选型[J]. 电线电缆, 2011(5): 19-22.
GONG Y C, HE X T, SUN J S, et al.The design and selection of high-voltage submarine power cable armor[J]. Wire & cable, 2011(5): 19-22.
[27] 王文超, 张建民, 赵囿林, 等. 扁钢丝铠装光纤复合海缆拉伸试验与仿真分析[J]. 高电压技术, 2019, 45(11): 3467-3473.
WANG W C, ZHANG J M, ZHAO Y L, et al.Tension test and simulation analysis on flat-steel-wire-armoured optical fiber composite submarine cable[J]. High voltage engineering, 2019, 45(11): 3467-3473.
[28] STEIN M.Large sample properties of simulations using Latin hypercube sampling[J]. Technometrics, 1987, 29(2): 143-151.