串联式集装箱重心偏移自适应修正算法研究-《计算机技术与发展》

文章信息/Info

作者:: 何锋¹ 宋小波¹; 2 刘忠杰¹ 周培莹¹ 蒋欣晟¹; [1]常州先进制造技术研究所机器人系统实验室[2]中国科学院合肥物质科学研究院先进制造技术研究所机器人系统实验室

Author(s):: HE Feng; SONG Xiao-bo ; LIU Zhong-jie ; ZHOU Pei-ying ; JIANG Xin-sheng; [1]Robot System Lab, Institute of Advanced Manufacturing Technology[2]Robot System Lab, Institute of Advanced Manufacturing Technology, Hefei Institutes of Physical Science, Chinese Academy of Sciences

Keywords:: tandem container; weight in motion; neural network; RBF; K-Mean clustering algorithm ; RLS algorithmngzhou

摘要:: 针对串联式集装箱分箱计重中因货物配置不匀导致的重心随机偏移问题,提出了一种基于径向基函数神经网络的自适应修正算法。该算法利用K-Mean聚类算法来确定RBF神经网络隐含层的中心向量;并采用RLS算法来调整隐含层与输出层之间的连接权值。该算法模型能针对各种车型并在各种车速下实现串联式集装箱的重心动态计算,从而获得准确的分箱重量。通过RBF及BP算法的仿真对比实验表明：基于RBF的修正算法具有更高的环境适应性和更低的计重误差率,能真正达到串联式集装箱重心自适应偏移纠正的目的

Abstract:: For the random gravity migration of the tandem container caused by the goods placed unevenly in sub-box weight,a self-ad- justing algorithm is proposed based on radio basis function neural network. K-Mean clustering algorithm is used for determining the pa- rameters of RBF in hidden layer,and RLS algorithm is adopted to update weights of connections between hidden layer and output layer. The center of gravity of tandem container can be calculated dynamically according to the algorithm model to various models an multiple speed,so that get the accurate weight of each container. By simulating and comparing with RBF and BP algorithms,the experiments pres- ent the best of environmental adaptation and the least of weight error of the self-adjusting algorithm based on RBF,achieve the purpose of self-adjusting correction for the tandem container＇ s gravity migration