基于改进GA-BP网络的系泊缆力预测建模与仿真
发布时间：2018-11-16 21:11
【摘要】：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。
[Abstract]:In order to meet the demand of berthing safety and early warning control of large open wharf, a kind of forecasting model of mooring ship cable force based on genetic algorithm and BP network is studied. Considering the environmental dynamic factors which affect the mooring force, the structure of the prediction model is determined by the statistical method of the right of use, and the learning method of the prediction model is improved by using the individual parent information and the local gradient information of the contemporary individual. Based on the improved prediction model, a prediction method for mooring ship cable force of large open wharf is proposed. The simulation results show that the performance of the improved mooring ship cable force prediction model has been improved in evolutionary algebra, maximum fitness and prediction accuracy, and the mean value of prediction error is less than 10, which meets the actual demand.
【作者单位】： 大连交通大学机械工程学院;大连交通大学软件学院;
【基金】：国家自然科学基金(61074029) 大连市计划(2014A11GX006)
【分类号】：TP18;U653.2;U675.92
本文编号：2336649
[Abstract]:In order to meet the demand of berthing safety and early warning control of large open wharf, a kind of forecasting model of mooring ship cable force based on genetic algorithm and BP network is studied. Considering the environmental dynamic factors which affect the mooring force, the structure of the prediction model is determined by the statistical method of the right of use, and the learning method of the prediction model is improved by using the individual parent information and the local gradient information of the contemporary individual. Based on the improved prediction model, a prediction method for mooring ship cable force of large open wharf is proposed. The simulation results show that the performance of the improved mooring ship cable force prediction model has been improved in evolutionary algebra, maximum fitness and prediction accuracy, and the mean value of prediction error is less than 10, which meets the actual demand.
【作者单位】： 大连交通大学机械工程学院;大连交通大学软件学院;
【基金】：国家自然科学基金(61074029) 大连市计划(2014A11GX006)
【分类号】：TP18;U653.2;U675.92
【相似文献】
相关期刊论文 前5条
1 王平;王彩芸;王文健;刘启跃;;GA-BP网络在钢轨磨损量预测中的应用[J];润滑与密封;2011年02期
2 周云龙;吴昱;;基于EMD与GA-BP网络的离心泵汽蚀故障诊断[J];化工自动化及仪表;2014年06期
3 王亚军;王旭东;周永勤;颜颐欣;;准抗毁化电源蓄电池SOC预测的GA-BP网络方法[J];电机与控制学报;2010年06期
4 白铁成;张任;齐立美;任滨;;小波包和GA-BP网络结合的红枣病害识别方法[J];哈尔滨理工大学学报;2011年06期
5 ;[J];;年期
相关硕士学位论文 前1条
1 代德宇;基于GA-BP网络的铜管生产过程能耗预测模型研究及应用[D];广东工业大学;2016年
，本文编号：2336649
本文链接：https://www.wllwen.com/kejilunwen/daoluqiaoliang/2336649.html
