|
|
Publications
Tang, H.Y., Ren, D.Y., Chen, B.Q. and Guedes Soares, C. (2025), A trimaran structure damage identification method based on machine learning, Ocean Engineering, Vol. 320, 120315.
A trimaran structure damage identification method based on machine learning is proposed. In the damage identification method, wavelet transform and improved adaptive threshold function are used to realise signal denoising and structural curvature difference based on fractal box dimension is calculated as a critical index to train a back-propagation neural network. The improved particle swarm optimisation is also adopted to jointly optimise the back-propagation neural network and the wavelet filter for identifying damage degree and location. The load data from a trimaran model test are extracted and combined with the finite element method to simulate the situation of multiple damage occurrences under different hull deformations. The advantages and reliability of the damage identification method have been finally demonstrated through comparative analysis. Applying this damage identification method will provide technical support for auxiliary decision-making and damage diagnosis of intelligent trimarans.
If you did not manage to obtain a copy of this paper: Request a copy of this article
For information about all CENTEC publications you can download: Download the Complete List of CENTEC Publications
|