The invention discloses a ship motion response prediction method based on a neural network, and the method comprises the following steps: (1) data collection and preprocessing: collecting motion posture data of a ship under different sea conditions, and carrying out the standardization processing of the data; (2) model construction: constructing an EMD-CNN-BiLSTM neural network prediction model; (3) training and optimization: training the model by using the divided data set; (4) predicting and verifying: verifying the trained model by using a test set, specifically, performing grading processing on data in the test set through an EMD method, predicting the decomposed data, then overlapping and combining the predicted data again, and comparing the data with original unprocessed test data, so as to obtain a test result; therefore, the accuracy of the model in the prediction task is evaluated. The ship motion response prediction precision can be improved, the good generalization ability and calculation efficiency are achieved, and the ship motion response prediction method has the important application value for improving the safety and stability of a ship.
一种基于神经网络的船舶运动响应预测方法,步骤如下:(1)数据收集与预处理:收集舰船在不同海况下的运动姿态数据,并对数据进行标准化处理;(2)模型构建:构建EMD‑CNN‑BiLSTM神经网络预测模型;(3)训练与优化:使用划分好的数据集对模型进行训练;(4)预测与验证:使用测试集对训练好的模型进行验证,具体是将测试集中的数据通过EMD方法进行分级处理后,再对这些分解后的数据进行预测,随后,将预测得到的数据重新叠加组合,并与原始未经处理的测试数据进行对比,以此来评估该模型在预测任务中的准确性。本发明不仅能够提高对舰船运动响应的预测精度,而且具有较好的泛化能力和计算效率,对于提高船舶的安全性和稳定性具有重要应用价值。
Ship motion response prediction method based on neural network
一种基于神经网络的船舶运动响应预测方法
2025-05-13
Patent
Electronic Resource
Chinese
Neural-network-based modelling and analysis for time series prediction of ship motion
Taylor & Francis Verlag | 2017
|Echo State Network Ship Motion Modeling Prediction Based on Kalman Filter
British Library Conference Proceedings | 2017
|