文献类型：期刊文献

英文题名：Nonlinear Real-Time Prediction of Metacentric Height of Ro-Ro Passenger Ships in Qiongzhou Strait Based on Improved Rbf Neural Network

作者：Liao, Shenghao[1]; Wang, Lijun[1,2]; Wang, Sisi[1]; Yin, Jianchuan[1]; Li, Ronghui[1]

机构：[1] Naval Architecture and Shipping College, Guangdong Ocean University, Zhanjiang, 524088, China; [2] Guangdong Provincial Key Laboratory of Intelligent Equipment for South China Sea Marine Ranching, Guangdong Ocean University, Zhanjiang, 524088, China

年份：2024

外文期刊名：SSRN

收录：EI(收录号：20240133011)

语种：英文

外文关键词：Correlation methods - Neural network models - Radial basis function networks - Ships

外文摘要：Addressing the complexities and real-time challenges in calculating ship metacentric height (GM), this study proposes an improved method using an optimized radial basis function (RBF) neural network for real-time GM prediction. To improve model generalization, leave-one-out cross-validation and early stopping strategies are employed to optimize the radial basis function. The study focuses on the Qiongzhou Strait Ro-ro passenger ship ‘Zijing No.11’ and selects four GM-related factors as neural network inputs using grey correlation analysis. The GM calculated by the empirical formula serves as the expected value, which is compared with predictions from various algorithms. Simulation results indicate that the improved RBF neural network exhibits lower prediction errors (MSE = 0.000425, MAPE ? 2024, The Authors. All rights reserved.