摘要
针对水下弹性目标声散射高精度、高效率求解需求,提出一种基于物理信息神经网络的建模方法,重点从网络结构、激活函数及损失权重分布等方面提升模型收敛性能。首先分析各区域配置点数对预测性能的影响;解耦流体域声压场与弹性体域位移场的物理约束,构建并行和顺序化网络架构,增益调节输出值,平衡不同物理场的特征量纲差异;引入自适应权重方法和Snake激活函数进一步提升模型效率。以二维弹性目标为算例的数值结果表明,当目标为圆形且频率为2409 Hz时,解耦并行模型较传统模型收敛效率提升78.8%。随频率和形状复杂度增加,解耦并行模型的收敛效率和泛化能力明显提升。
To achieve high-accuracy and high-efficiency solutions for acoustic scattering from underwater elastic targets,a physicsinformed neural network–based acoustic scattering modeling method is proposed,with emphasis on improving convergence performance through the network architecture,activation functions,and loss weight distribution.The influence of the number of configuration points in each region on prediction performance is analyzed.The physical constraints of the acoustic pressure field in the fluid domain and the displacement field in the elastic body domain are decoupled to construct parallel and sequential network architectures.Gain adjustment is applied to output values to balance the characteristic dimension differences of different physical fields.An adaptive weight method and Snake activation function are introduced to further enhance model efficiency.Numerical simulations are conducted on two-dimensional elastic targets.The results show that when the target is circular and the frequency is 2409 Hz,the convergence efficiency of the decoupled parallel model is 78.8%higher than that of the traditional model.As the frequency and shape complexity increase,the decoupled parallel model demonstrates significant improvements in convergence efficiency and generalization ability.
作者
刘梦婷
李卓然
秦志亮
于盛齐
马本俊
王志勇
郑毅
LIU Mengting;LI Zhuoran;QIN Zhiliang;YU Shengqi;MA Benjun;WANG Zhiyong;ZHENG Yi(National Key Laboratory of Underwater Acoustic Technology,Harbin Engineering University,Harbin,150001;Key Laboratory of Marine Information Acquisition and Security(Harbin Engineering University),Ministry of Industry and Information Technology,Harbin,150001;College of Underwater Acoustic Engineering,Harbin Engineering University,Harbin,150001)
出处
《声学学报》
北大核心
2026年第1期270-286,共17页
Acta Acustica
基金
青岛市自然科学基金项目(25-1-1-182-zyyd-jch)
国家自然科学基金项目(42404129)
泰山学者工程项目
山东省自然科学基金项目(ZR2024QD082)资助。
关键词
物理信息神经网络
水下弹性目标
声散射
解耦并行模型
Physics-informed neural network
Underwater elastic target
Acoustic scattering
Decoupled parallel model
