摘要
为优化艉轴管镗孔的镗削工艺,研究镗削用量和加工过程中各影响因素对艉轴管尺寸误差的影响,采用基于L-M算法的BP神经网络对影响艉轴管镗孔的各因素进行分析,得到艉轴管镗孔误差与各因素之间的非线性关系。建立多输入单输出的BP神经网络模型,并应用镗孔的实际数据对其进行训练。采用正交试验法得到相应的加工数据,对预测模型的有效性进行验证,结果表明,采用基于L-M算法的BP神经网络建立的艉轴管镗孔误差预测模型,能对艉轴管的镗孔误差进行较为准确的预测。
In order to optimize the boring process of ship’s stern tube boring, and to study the influence of boring parameters, various factors of machining process and the size error of stern tube, the BP neural network based on L-M algorithm is used to analyze the various factors affecting the boring of stern tube, and the nonlinear relationship between the boring error of stern tube and these influencing factors is obtained, and multi input single output is established, the results show that the neural network can be used to predict the error of the stern tube boring.
作者
董子彰
邓啸尘
杨振
刘建峰
周宏
DONG Zizhang;DENG Xiaochen;YANG Zhen;LIU Jianfeng;ZHOU Hong(School of Naval Architecture and Ocean Engineering,Jiangsu University of Science and Technology,Zhenjiang 212003,Jiangsu,China;Shanghai Waigaoqiao Shipbuilding Co.,Ltd.,Shanghai 200137,China)
出处
《船舶工程》
CSCD
北大核心
2021年第9期123-126,131,共5页
Ship Engineering
基金
船舶分段智能制造装备解决方案及关键共性技术研究(工信部装函2018[473]号)。
关键词
BP神经网络
艉轴管
圆柱度
误差预测
BP neural network
stern tube
cylindricity
error prediction
