Abstract The working efficiency and economic benefit of trailing suction dredge are directly dependent on the earth production, so prediction of earth production is of great significance in the mechanism analysis and efficiency optimization of the trailing suction dredge. Suction dredger dredging process mode is a complex, non-linear dynamic model, and the model is affected by a variety of factors. This paper presents a genetic algorithm to improve the BP neural network model that is used to predict dredger production. In order to overcome the shortcomings of traditional BP neural network training time long and easy to fall into local minimum, this paper uses genetic algorithm to optimize the initial weights and thresholds of BP neural network for dredger production prediction. The simulation results show that the genetic BP neural network has a better fitting ability. Compared with the BP neural network, it has the characteristics of good global search ability and high accuracy. The result shows that genetic BP neural network can accurately predict the production.
A Genetic Neural Network Approach for Production Prediction of Trailing Suction Dredge
2017-01-01
9 pages
Article/Chapter (Book)
Electronic Resource
English
New Trailing Suction Hopper Dredge for HAM
British Library Online Contents | 1996
Articulated tug barge, trailing suction hopper dredge system
European Patent Office | 2015
|New Trailing Suction Hopper Dredge Ordered by Jan De Nul
British Library Online Contents | 1997
World's largest Trailing Suction Hopper Dredge to Feature GIW Pumps
British Library Online Contents | 1996
Launching of 18,000 M^3 Trailing Suction Hopper Dredge Gerardus Mercator
British Library Online Contents | 1996