【摘要】 船舶冲击响应具有短时性和复杂性,通常使用冲击响应谱(SRS)作为其分析工具。为克服传统SRS求解方法存在的计算速度与精度之间的矛盾,文中提出一种基于深度学习的SRS快速求解器,并根据SRS的特点设计自适应阈值选择机制,提升求解器计算精度。对比求解器得到的SRS与采用传统方法计算的结果,两者显示出高度一致性,从而验证了求解器的有效性。此外,文中在求解过程中引入L2正则化技术,有效避免了过拟合现象的发生,进一步增强了求解器的鲁棒性。更多还原

【Abstract】 Due to the short duration and complexity of ship shock responses, the shock response spectrum(SRS) is commonly used as a tool for analyzing these responses. To address the conflict between calculation speed and accuracy inherent in traditional SRS solving methods, this paper proposed a deep learning-based fast solver for the SRS. An adaptive threshold selection mechanism tailored to the characteristics of the SRS was designed to improve the solver’s calculation accuracy. A comparison between the SRS obtained by the proposed solver and the results calculated using traditional methods demonstrated a high degree of consistency, validating the effectiveness of the solver. Additionally, L2 regularization was introduced in the solution process, effectively preventing overfitting and further enhancing the robustness of the solver.更多还原