The invention provides a ship heaving motion prediction system and a ship heaving motion prediction method based on a Conv-Bi-LSTM model. The method comprises the following steps: acquiring historical motion data of a ship, establishing a data set of motion information, preprocessing the data set, randomly splitting the data set, and acquiring a training data set and a test data set; a Conv-Bi-LSTM model is adopted to construct a ship heave prediction model, the training data set is adopted to train a Conv-Bi-LSTM network, and the ship heave prediction model is obtained; inputting the test data set into a ship heaving motion prediction model for prediction to obtain test data prediction precision, and evaluating the performance of the model by using average error (MAE), mean square error (MSE), root mean square error (RMSE) and average absolute percentage error (MAPE) evaluation indexes; according to the method, historical motion information of multiple degrees of freedom serves as input of the model, ship heaving is comprehensively predicted, forward time state information and reverse time state information of a motion time sequence are fully utilized, and the prediction precision of heaving motion is improved.
本发明提出了一种基于Conv‑Bi‑LSTM模型的船舶升沉运动预测系统及预测方法;获取船舶历史运动数据,建立运动信息的数据集,对所述数据集进行预处理,对数据集进行随机拆分,获取训练数据集和测试数据集;采用Conv‑Bi‑LSTM模型构建船舶升沉预测模型,训练数据集训练Conv‑Bi‑LSTM网络,获得船舶升沉预测模型;将所述测试数据集输入船舶升沉运动预测模型进行预测,获取到测试数据预测精度,使用平均误差MAE、均方误差MSE、均方根误差RMSE和平均绝对百分比误差MAPE评价指标评价模型的性能;本发明把多个自由度历史运动信息当做模型的输入,对船舶升沉进行综合预测,充分利用了运动时间序列的正向反向两个时间状态信息,提高了升沉运动的预测精度。
Conv-Bi-LSTM model-based ship heaving motion prediction system and prediction method
一种基于Conv-Bi-LSTM模型的船舶升沉运动预测系统及预测方法
2023-06-23
Patent
Electronic Resource
Chinese
Instant traffic flow prediction method based on Conv-LSTM
European Patent Office | 2023
|Traffic prediction method based on multi-graph gating convolution and Conv-LSTM
European Patent Office | 2025
|Ship crane heaving compensation method based on hanger heaving motion forecast
European Patent Office | 2015
|A Deep Learning Model with Conv-LSTM Networks for Subway Passenger Congestion Delay Prediction
DOAJ | 2021
|