基于神经网络的海冰弯曲强度计算参数确定及锥体破冰数值研究

PDF(4142 KB)

振动与冲击 ›› 2025, Vol. 44 ›› Issue (1) : 41-50.

振动理论与交叉研究

基于神经网络的海冰弯曲强度计算参数确定及锥体破冰数值研究

朱圣涛1，邹璐*1,2，邹早建1,2，邹明1

作者信息 +

Determination of sea ice bending strength calculation parameters based onneural network and numerical study on ice-breaking with a cone

ZHU Shengtao1, ZOU Lu*1,2, ZOU Zaojian1,2, ZOU Ming1

Author information +

文章历史 +

摘要

为构建粘聚单元物理参数与海冰弯曲强度之间的关系，提出一种基于神经网络的回归模型用于海冰弯曲强度计算参数的确定。首先，基于有限元法及粘聚单元法对海冰三点弯曲试验进行数值模拟并验证方法的有效性。然后，选择五个影响参数，采用拉丁超立方抽样算法生成427个样本，通过数值模拟得到其对应的海冰弯曲强度，构建神经网络的数据集。在此基础上，采用多层感知器神经网络对所有样本预报结果进行训练，得到预报海冰弯曲强度的回归模型。以此建立与试验海冰弯曲强度相近的层冰数值模型，并考虑流体浮力和拖曳力对碎冰的作用，对不同参数影响下的锥体层冰相互作用进行数值模拟及分析。结果显示：锥体受到层冰纵向力的均值、标准差以及峰值均随碰撞速度、锥体水线面直径和锥体角度的增加而增大。

Abstract

To establish the relationship between physical parameters of cohesive elements and bending strength of the sea ice, a regression model based on neural networks is proposed to determine the calculation parameters for predicting the bending strength of sea ice. Firstly, the numerical simulations of three-point bending test of sea ice are conducted applying finite element method and cohesive element method, and the effectiveness of the method is verified. Then, five influencing parameters are selected and 427 samples are generated using the Latin hypercube sampling algorithm. The corresponding bending strengths of sea ice in these samples are obtained through numerical simulations and the database of neural networks is established. On this basis, the multilayer perceptron neural network is used to train the prediction results for all samples, and a regression model for predicting the bending strength of sea ice is obtained. Consequently, a numerical model of level ice with the bending strength similar to that of the sea-ice tests is constructed. Moreover, the impacts of buoyancy and drag force by the fluid on the broken ice are considered in the numerical model as well, and the interactions between the cone and the level ice are simulated and analyzed considering the impacts by different parameters. The results indicate that the mean value, standard deviation, and peak values of the longitudinal ice force acting on the cone tend to be larger with the increase of collision velocity, cone waterplane diameter, and cone angle.

导出引用

朱圣涛1, 邹璐1, 2, 邹早建1, 2, 邹明1. 基于神经网络的海冰弯曲强度计算参数确定及锥体破冰数值研究[J]. 振动与冲击, 2025, 44(1): 41-50

ZHU Shengtao1, ZOU Lu1, 2, ZOU Zaojian1, 2, ZOU Ming1. Determination of sea ice bending strength calculation parameters based onneural network and numerical study on ice-breaking with a cone[J]. Journal of Vibration and Shock, 2025, 44(1): 41-50

参考文献

[1] 武文华, 于佰杰, 岳前进. 冰锥作用位置对冰弯曲破坏模式影响数值分析[J]. 大连理工大学学报, 2009, 49(03): 313-6.
WU Wen-hua, YU Bai-jie, YUE Qian-jin. Numerical analysis for position-effect of ice-cone interaction on ice bending failure modes[J]. Journal of Dalian University of Technology, 2009, 49(03): 313-6.
[2] JEON S, KIM Y. Numerical simulation of level ice-structure interaction using damage-based erosion model[J]. Ocean Engineering, 2021, 220: 108485.
[3] GOGOLADZE D Z, BEKKER A T. Numerical modeling of the ice-conical structure interaction process using element erosion technique[J]. IOP Conference Series: Earth and Environmental Science, 2022, 988(5): 052056.
[4] WANG C, HU X H, TIAN T P, et al. Numerical simulation of ice loads on a ship in broken ice fields using an elastic ice model[J]. International Journal of Naval Architecture and Ocean Engineering, 2020, 12: 414-27.
[5] SONG M, JIANG Z, LIU K, et al. Dynamic response analysis of a monopile-supported offshore wind turbine under the combined effect of sea ice impact and wind load[J]. Ocean Engineering, 2023, 286: 115587.
[6] 钱晓刚. 冰载荷下艏部结构响应与耐撞性能研究[D]. 镇江：江苏科技大学，2019.
QIAN Xiao-gang. Research on the Structural Response and Crashworthiness of the Ankle under Ice Load[D]. Zhen Jiang: Jiangsu University of Science and Technology, 2019.
[7] LU W J, LUBBAD R, LøSET S. Simulating ice-sloping structure interactions with the cohesive element method[J]. Journal of Offshore Mechanics and Arctic Engineering, 2014, 136(3): 031501.
[8] WANG F, ZOU Z J, ZHOU L, et al. A simulation study on the interaction between sloping marine structure and level ice based on cohesive element model[J]. Cold Regions Science and Technology, 2018, 149: 1-15.
[9] 焦博阳. 基于粘聚单元法的结构与层冰碰撞模拟[D]. 大连: 大连理工大学, 2022.
JIAO Bo-yang. Simulation of Structure Ice Collision Based on Cohesive Element Method[D]. Dalian: Dalian University of Technology, 2022.
[10] 詹开宇, 曹留帅, 万德成. 基于黏聚单元法计算分析海洋平台锥形立柱冰载荷[J]. 海洋工程, 2021, 39(04): 62-9.
ZHAN Kai-yu, CAO Liu-shuai, WAN De-cheng. Cohesive element method for ice load on conical structures[J]. The Ocean Engineering, 2021, 39(04): 62-9.
[11] HAN S J, YANG B Y, YANG B R, et al. Numerical simulation of heterogeneous ice sheet-structure interaction based on cohesive element method[J]. Applied Ocean Research, 2024, 145: 103942.
[12] ZHANG J H, WANG X Y, SUN K, et al. Ice-induced vibration analysis of offshore platform structures based on cohesive element method[J]. Journal of Marine Science and Engineering, 2024, 12(1): 28.
[13] LIU Y, SHI W, WANG W, et al. Investigation on the interaction between ice and monopile offshore wind turbine using a coupled CEM–FEM model[J]. Ocean Engineering, 2023, 281: 114783.
[14] 姬贺港, 张健, 李越. 基于黏聚单元法的冰-柱碰撞流固耦合计算方法研究[J]. 振动与冲击, 2023, 42(11): 42-7+74.
JI He-gang, ZHANG Jian, LI Yue. Fluid-structure interaction calculation method for ice-column collision based on cohesive element method[J]. Jounal of Vibration and Shock, 2023, 42(11): 42-7+74.
[15] 王祥. 基于粘聚单元法的海洋牧场平台冰撞载荷研究[D]. 镇江: 江苏科技大学, 2023.
WANG Xiang. Research on Ice Impact Loads on Marine Ranch Platform Based on Cohesive Element Method[D]. Zhen Jiang: Jiangsu University of Science and Technology, 2023.
[16] ROSENBLATT F. The perceptron: a probabilistic model for information storage and organization in the brain[J]. Psychological Review, 1958, 65(6): 386-408.
[17] RUMELHART D E, HINTON G E, WILLIAMS R J. Learning representations by back-propagating errors[J]. Nature, 1986, 323(6088): 533-6.
[18] 于嵩松, 曾二贤, 刘文勋, 等. 基于神经网络算法的经济型导管架结构冰振响应预测研究[J]. 石油工程建设, 2024, 50(01): 14-20.
YU Song-song, ZENG Er-xian, LIU Wen-xun, et al. Ice-induced vibration reponse forecast research of economical jacket platform based on machine learning methods[J]. Petroleum Engineering Construction, 2024, 50(01): 14-20.
[19] 潘栎光. 某型破冰船阻力性能优化研究[D]. 哈尔滨: 哈尔滨工程大学, 2023.
PAN Li-guang. Study on Optimization of Resistance Performance of an Icebreaker[D]. Harbin: Harbin Engineering University, 2023.
[20] 孟丁丁, 陈晓东, 季顺迎. 基于循环神经网络的海冰弯曲强度预测分析[J]. 力学与实践, 2022, 44(03): 580-9.
MENG Ding-ding, CHEN Xiao-dong, JI Shun-ying. Prediction and analysis of flextural strength of sea ice based on recurrent neural network[J]. Mechanics in Engineering, 2022, 44(03): 580-9.
[21] HILLERBORG A, MODéER M, PETERSSON P E. Analysis of crack formation and crack growth in concrete by means of fracture mechanics and finite elements[J]. Cement and Concrete Research, 1976, 6(6): 773-81.
[22] 卢巍. 海冰弯曲破坏的近场动力学数值计算方法研究[D]. 哈尔滨: 哈尔滨工程大学, 2017.
LU Wei. The Study of the Numerical Simulation Method of Peridynamic Based on the Bending Fracture of Sea Ice[D]. Harbin: Harbin Engineering University, 2017.
[23] 王峰. 基于粘聚单元模型的海洋结构物与平整冰相互作用数值研究[D]. 上海: 上海交通大学, 2019.
WANG Feng. Numerical Research on the Interactions between Marine Structures and Level Ice Based on Cohesive Element Model[D]. Shanghai: Shanghai Jiao Tong University, 2019.
[24] 龙雪. 海洋结构物作用下海冰破坏模式及冰载荷的离散元分析[D]. 大连: 大连理工大学, 2019.
LONG Xue. Discrete Element Analysis of Sea Ice Failure Mode and Ice Load during the Interaction with Marine Structure[D]. Dalian: Dalian University of Technology, 2019.
[25] CHEN Z, HE Y P, REN Y P, et al. Numerical simulation of the interaction between icebreaker and level ice with different flexural strength[C]//International Ocean and Polar Engineering Conference, ISOPE, 2021: ISOPE-I-21-1297.
[26] TIMCO G W, WEEKS W F. A review of the engineering properties of sea ice[J]. Cold Regions Science and Technology, 2010, 60(2): 107-29.
[27] DEMPSEY J P, MU Z, COLE D M. In-situ fracture of first-year sea ice in McMurdo Sound[C]. Proceedings of the 17th IAHR Symposium on Ice. 2004, 2: 299-306.
[28] DEMPSEY J P, XIE Y, ADAMSON R M, et al. Fracture of a ridged multi-year Arctic sea ice floe[J]. Cold Regions Science and Technology, 2012, 76: 63-68.
[29] KÄRNÄ T, LUBBAD R, LØSET S, et al. Ice failure process on fixed and compliant cones[C]//HYDRALAB III Joint User Meeting, Hannover, Germany. 2010: 1-4.
[30] LU W J. Floe Ice-Sloping Structure Interactions[M]. NTNU, 2014.