基于遗传BP神经网络的耙吸挖泥船产量预测研究

Prediction of Dry Earth Productivity of Trailing Suction Dredger Based on Genetic BP Neural Network

耙吸挖泥船的工作效率和经济效益直接取决于干土方的生产率,因此预测干土方生产率对耙吸式挖泥船疏浚机构分析和效率优化具有重要意义。耙吸挖泥船疏浚过程模式是一种复杂的非线性动力学模型,该模型受多种因素的影响,为了减少各种因素带来的影响,我们采用通过遗传算法(GA)优化的BP神经网络来构建干土方生产率的预测模型。为了评估预测模型的性能,未优化的BP神经网络预测模型也用于实验比较。实验结果表明,遗传算法优化后的神经网络预测模型能够满足预测需求,训练好的神经网络可以作为干土方生产率预测的有用工具。

The productivity and economic benefits of the sucking dredger are directly dependent on the productivity of the dry earth,so it is important to predict the productivity of the dry earth to improve the analysis and efficiency optimization of the dredger.The dredging process model is a complex nonlinear dynamic model. The model is affected by many factors. In order to reduce the influence of various factors,we adopt BP neural network optimized by genetic algorithm（GA）Network to construct the prediction model of dry earth productivity. In order to evaluate the performance of the prediction model,the unpredictable BP neural network prediction model is also used for experimental comparison. The experimental results show that the neural network prediction model optimized by genetic algorithm can meet the forecast demand. The trained neural network can be used as a useful tool for predicting the productivity of dry earth.