Wu Shiji, Huang Xiufeng, Xu Rongwu, Yu Wenjing, Cheng Guo
Laboratory of Vibration and Noise, Naval University of Engineering, Wuhan 430033, China.
National Key Laboratory of Vibration and Noise on Ship, Naval University of Engineering, Wuhan 430033, China.
Sensors (Basel). 2024 Sep 19;24(18):6060. doi: 10.3390/s24186060.
In order to achieve impact load localization of complex structures such as ships, this paper proposes a multi-scale feature fusion convolutional neural network (MSFF-CNN) method for impact load localization. An end-to-end machine learning model is used, where the raw vibration signals of impact loads are directly fed into the network model to avoid the process of feature extraction. Automatic feature learning and feature concatenation of the signal are achieved through four independent convolutional layers, each using a different size of convolutional kernel. Data normalization and L2 regularization techniques are introduced to enhance the data and prevent overfitting. Classification and localization of impact loads are accomplished using a softmax classification layer. Validation experiments are carried out using a ship's stern compartment model. Our results show that the classification and localization accuracy of the impact load sample group of MSFF-CNN reaches 94.29% compared with a traditional CNN. The method further improves the ability of the network to extract state features, takes local perception and global vision into account, effectively improves the classification ability of the model, and has good prospects for engineering applications.
为实现船舶等复杂结构的冲击载荷定位，本文提出一种用于冲击载荷定位的多尺度特征融合卷积神经网络（MSFF-CNN）方法。采用端到端的机器学习模型，将冲击载荷的原始振动信号直接输入网络模型，避免特征提取过程。通过四个独立的卷积层实现信号的自动特征学习和特征拼接，每个卷积层使用不同大小的卷积核。引入数据归一化和L2正则化技术来增强数据并防止过拟合。使用softmax分类层完成冲击载荷的分类和定位。利用船舶艉部舱室模型进行验证实验。结果表明，与传统卷积神经网络相比，MSFF-CNN冲击载荷样本组的分类和定位准确率达到94.29%。该方法进一步提高了网络提取状态特征的能力，兼顾局部感知和全局视野，有效提升了模型的分类能力，具有良好的工程应用前景。
