基于改进GA-BP网络的系泊缆力预测建模与仿真

Modeling and Simulation of Mooring Force Prediction Based on Improved GA-BP Network

针对大型开敞式码头系靠泊安全保障和预警控制需求,研究了一类基于遗传算法和BP网络的系泊船舶缆力预测模型。考虑影响系泊缆力的环境动力因素,使用权值统计法确定了预测模型的结构;利用个体父代信息和当代个体的局部梯度信息对预测模型的学习方法进行了改进;基于改进的预测模型,提出了大型开敞式码头系泊船舶缆力预测方法。仿真结果表明:改进后的系泊船舶缆力预测模型在进化代数、最大适应度和预测精度等方面的性能均有所提高,且预测误差均值低于10%,满足实际需求。

According to the mooring security and early warning control requirement of the large open sea terminal, a ship mooring force prediction model based on genetic algorithm and BP network was studied. Environmental dynamic factors were considered and a model structure was determined by a weight statistics method; the learning method was improved by individual parent information and contemporary individual local gradient information; according to the improved model, a ship mooring force prediction method of the open sea terminal was proposed. The simulation results show that the performance of the prediction model has improved in the iteration number, the largest fitness and prediction accuracy. The average error is less than 10% which satisfies the actual demand well.