论文部分内容阅读
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。
Aiming at the requirements of berthing security and early warning control in large open wharf system, a kind of mooring ship cable force prediction model based on genetic algorithm and BP network is studied. Considering the environmental dynamic factors that affect the mooring line force, the structure of the forecasting model is determined by statistical method of weighting. The learning methods of the forecasting model are improved by using the parental information of individuals and the local gradient information of contemporary individuals. Based on the improved forecasting model , Proposed a method for predicting the cable force of large open dock mooring ship. The simulation results show that the performance of mooring ship’s cable force prediction model is improved in terms of evolutionary algebra, maximum fitness and prediction accuracy, and the mean of prediction error is less than 10%, which meets the actual needs.