Prediction of Cutter-Suction Dredger Production Based on Double Hidden Layer BP Neural Network
YANG Jinbao
NI Fusheng
WEI Changyun
ZHENG Qingyun
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.
Keywords：cutter suction dredgerprediction of productionBP neural networkdouble hidden layerLM algorithm
Publication Date：2016-01-01
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：4( 1234-1237 )