基于改进神经网络的船舶姿态准确预报技术
|
摘要
为了有效解决当前船舶姿态预测准确性问题,结合当前船舶姿态数据特征,改进传统神经网络并以此为基础建立新型船舶姿态预报技术。重构神经网络格式特征区,添加脉冲输出和神经网络数据放大和衰减参数量,构建耦合神经网络作为主要计算网络,结合达尔文进化算法和传统遗传算法特征,构建交叉概率算法,顶替传统经验算法获取放大衰减真实值,通过PC端数据传输和样本导入,实现船舶姿态准确预测。仿真实验数据表明,改进后的神经网络船舶姿态预报技术对于船舶横纵斜度的预测均提高30%以上,达到了提高船舶姿态预测准确度的目标。
In order to effectively solve the problem of the accuracy of the current ship attitude prediction, combining with the current ship attitude data characteristics, the traditional neural network was improved and a new type of ship attitude prediction technology was established based on this. Reconstructing neural network format feature area, adding pulse output data and the number of amplification and attenuation, the neural network and the construction of coupling neural network as the main computing network, combined with the feature of Darwinian evolution algorithm and traditional genetic algorithm, build crossover probability algorithm, replace traditional experience algorithm for amplification attenuation real value, through the PC sample data transfer and import, to realize attitude accurately forecast of the ship. The simulation results show that the improved neural network ship attitude prediction technology can improve the prediction of ship attitude by more than 30%.
In order to effectively solve the problem of the accuracy of the current ship attitude prediction, combining with the current ship attitude data characteristics, the traditional neural network was improved and a new type of ship attitude prediction technology was established based on this. Reconstructing neural network format feature area, adding pulse output data and the number of amplification and attenuation, the neural network and the construction of coupling neural network as the main computing network, combined with the feature of Darwinian evolution algorithm and traditional genetic algorithm, build crossover probability algorithm, replace traditional experience algorithm for amplification attenuation real value, through the PC sample data transfer and import, to realize attitude accurately forecast of the ship. The simulation results show that the improved neural network ship attitude prediction technology can improve the prediction of ship attitude by more than 30%.
引文
[1]宋蕙慧,于国星,曲延滨.基于扩展卡尔曼滤波算法的船舶姿态监测预报系统设计(英文)[J].中国惯性技术学报,2018,26(1):6-12.
[2]刘伟丽.基于神经网络的内河航道船舶交通流量预测方法研究[J].舰船科学技术,2018,40(1A):52-54.
[3]刘杰.基于闭环增益成形算法和神经网络算法的船舶运动控制器设计[J].舰船科学技术,2018,40(5A):206-208.
[4]彭刚,杨诗琪,黄心汉,等.改进的基于区域卷积神经网络的微操作系统目标检测方法[J].模式识别与人工智能,2018,31(2):142-149.
[2]刘伟丽.基于神经网络的内河航道船舶交通流量预测方法研究[J].舰船科学技术,2018,40(1A):52-54.
[3]刘杰.基于闭环增益成形算法和神经网络算法的船舶运动控制器设计[J].舰船科学技术,2018,40(5A):206-208.
[4]彭刚,杨诗琪,黄心汉,等.改进的基于区域卷积神经网络的微操作系统目标检测方法[J].模式识别与人工智能,2018,31(2):142-149.