计算机与数字工程2016，Vol.45Issue(7)：1234-1237,4.DOI:10.3969/j.issn.1672-9722.2016.07.009
基于双隐含层BP神经网络的绞吸挖泥船产量预测
Prediction of Cutter-Suction Dredger Production Based on Double Hidden Layer BP Neural Network
杨金宝 1倪福生 2魏长赟 1郑庆云2
作者信息
- 1. 河海大学机电工程学院 常州 213022
- 2. 疏浚教育部工程研究中心 常州 213022
- 折叠
摘要
Abstract
The production of a cutter suction dredger directly determines the efficiency of the project.Therefore,it is meaningful to research the production prediction.The dredging conditions of cutter suction dredges are non-constant and yield calculation is extremely complex during dredging operations.Thus,the BP neural network model which owns double hidden layers based on Levenberg-Marquardt algorithm is put forward to predict the yield of cutter suction dredgers.In terms of single hidden layer,the double hidden layer BP neural network is able to improve the performance of the network,thereby improving the accuracy of model predictions.On the basis of the input factors of the electric current of cutter,velocity of pipe line,the degree of vacuum,the swing speed and the output factors of slurry density,this paper establishes the yield pre-diction model.The results show that the predicting result is more accurate to the double hidden layer BP neural network and it can provide an effective method for predicting the yield dredger.关键词
绞吸挖泥船/产量预测/BP神经网络/双隐含层/Levenberg-Marquardt算法Key words
cutter suction dredger/prediction of production/BP neural network/double hidden layer/LM algorithm分类
机械制造引用本文复制引用
杨金宝,倪福生,魏长赟,郑庆云..基于双隐含层BP神经网络的绞吸挖泥船产量预测[J].计算机与数字工程,2016,45(7):1234-1237,4.
