Search

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.

In addressing the challenging issue of impact source localization for large-scale anisotropic stiffened compartmental cylindrical shell structures, this paper presents a novel impact localization method. The method is based on a time-reversal virtual focusing triangulation approach and does not rely on prior knowledge of the structure or specific measurements of wave velocity. By employing energy power filtering to select key sensors, wavelet packet decomposition is utilized to extract narrowband Lamb wave signals, which are then synthesized. Further enhancement of signal recognition is achieved through time-reversal amplification techniques. Experimental results demonstrate that under non-motorized operating conditions, this method achieves an average error of 0.89 m. Under motorized operating conditions, the average error is 1.12 m. Although the presence of background noise leads to an increase in error, the overall localization performance is superior to traditional triangulation methods. Additionally, selecting the top three sensors in terms of energy power ranking can more accurately record impact response.

In order to comprehensively evaluate and analyze the effectiveness of various heuristic intelligent optimization algorithms, this research employed particle swarm optimization, wind driven optimization, grey wolf optimization, and one-to-one-based optimizer as the basis. It applied 22 benchmark test functions to conduct a comparison and analysis of performance for these algorithms, considering descriptive statistics such as convergence speed, accuracy, and stability. Additionally, time and space complexity calculations were employed, alongside the nonparametric Friedman test, to further assess the algorithms. Furthermore, an investigation into the impact of control parameters on the algorithms’ output was conducted to compare and analyze the test results under different algorithms. The experimental findings demonstrate the efficacy of the aforementioned approaches in comprehensively analyzing and comparing the performance on different types of intelligent optimization algorithms. These results illustrate that algorithm performance can vary across different test functions. The one-to-one-based optimizer algorithm exhibited superior accuracy, stability, and relatively lower complexity.