摘要
针对船舶多自由度设备在爆炸冲击载荷下的响应分析难题,文中提出了一种基于深度学习的冲击响应预测模型。传统单自由度模型无法高效分析多自由度系统的复杂冲击响应,而该模型通过深度学习技术,特别是利用神经网络的数据特征提取和非线性建模能力,从数值仿真数据中学习冲击谱与输入冲击载荷的关联,实现了对船舶结构中关键点冲击响应谱的高效准确计算。该方法弥补了现有模型在处理多自由度设备时的不足,满足了对复杂系统冲击响应快速准确分析的需求。实验结果表明,该模型能准确预测多自由度设备的冲击响应谱,与仿真数据的相对误差控制在8%以内,有效解决了传统模型在多自由度系统分析中的局限性。
To analyze the response of multi-degree-of-freedom ship equipment under explosive shock loads,this study proposed a deep learning-based shock response prediction model.Traditional single-degree-of-freedom models struggle to efficiently analyze the complex shock responses of multi-degree-of-freedom systems.By leveraging deep learning technology,especially the data feature extraction and nonlinear modeling capabilities of neural networks,this model learned the correlation between shock spectra and input shock loads from numerical simulation data,enabling efficient and accurate calculation of shock response spectra at critical points in ship structures.This approach overcame the limitations of existing models in handling multi-degree-of-freedom equipment and met the demand for rapid and precise analysis of complex system shock responses.Experimental results show that the model can accurately predict the shock response spectra of multi-degree-offreedom equipment,with a relative error of less than 8%compared to simulation data,effectively resolving the bottlenecks of traditional models in multi-degree-of-freedom system analysis.
作者
黄沁怡
朱炜
马峰
陈思
王爽
HUANG Qinyi;ZHU Wei;MA Feng;CHEN Si;WANG Shuang(School of Mechatronical Engineering,Beijing Institute of Technology,Beijing 100081,China)
出处
《水下无人系统学报》
2025年第4期623-629,共7页
Journal of Unmanned Undersea Systems
基金
国家自然基金重点项目资助(U20A2071)
爆炸科学与安全防护全国重点实验室自主课题重点项目(ZDKT24-01).
关键词
爆炸冲击
冲击响应
深度学习
多自由度设备
explosive shock
shock response
deep learning
multi-degree-of-freedom equipment
