基于小波变换和GRU神经网络的系泊缆力预测  

Mooring Cable Force Prediction based on Wavelet Transform and GRU Neural Network

作　　者：宋旭东[1] 王雪 伊卫国[1] SONG Xudong;WANG Xue;YI Weiguo(Software Institute,Dalian Jiaotong University,Dalian 116028,China)

机构地区：[1]大连交通大学软件学院,辽宁大连116028

出　　处：《大连交通大学学报》2020年第6期91-94,共4页Journal of Dalian Jiaotong University

基　　金：辽宁省自然科学基金资助项目(2019-ZD-0105)。

摘　　要：为保障船舶系泊作业的安全,有必要提高系泊缆力预测结果的准确性.考虑到缆绳受多方面因素影响受力非线性特征显著的问题,使用小波变换处理缆绳缆力,将其分为多个平稳子序列,再利用循环神经网络RNN中的GRU进行预测,多个平稳子序列进行预测后得到的预测结果通过小波重构运算最终得到所预测的缆绳缆力.通过数据对比发现小波变换处理后经过GRU预测的缆力与直接经过GRU预测的结果相比准确性高,具有一定的应用价值.In order to ensure the safety of ship mooring operation,it is necessary to improve the accuracy of the mooring line force prediction results.Considering that cable is affected by many factors,the nonlinear characteristics of force are significant.Wavelet transform is used to deal with cable force,multiple stationary subsequences are divided,and then the GRU in the recurrent neural network RNN is used for the prediction.The prediction results obtained by the prediction of multiple stationary subsequences are finally obtained by the wavelet reconstruction to obtain the predicted cable strength.Through data comparison,it is found that the cable strength predicted by the GRU after wavelet transform processing is more accurate than the result directly predicted by GRU.

关 键 词：缆力预测 循环神经网络 小波变换 

分 类 号：U675.92[交通运输工程—船舶及航道工程]