摘要
为了揭示加工工艺参数与结合面接触参数非线性关系,首先以加工工艺参数为输入层,以结合面表面形貌参数为输出层,建立了基于深度信念网的表面形貌预测模型,然后应用预测结果采用分形理论建立了结合面参数模型,最后分析了铣削工艺参数、磨削工艺参数对结合面接触参数的影响规律。应用预测模型可实现任意输入加工工艺参数即可获得高精度的结合面接触参数,建立的结合面接触参数与加工工艺参数非线性预测模型,为指导结合面加工工艺参数选择、优化提供了理论基础。
The objective of this paper is to reveal the nonlinear relationship between the process parameters and the contact parameters of the joint surface. First the prediction model based on the deep belief network is established by using the processing parameters as the input layer and the surface topography parameters as the output layer. Then the fractal theory is used to set up the parameters of the joint surface based on the prediction results. Finally the influences of cutting parameters and grinding parameters on the contact parameters are analyzed. Through using the training model of deep Belief Networks,the parameters of surface topography on joint surface could be obtained by arbitrarily inputting machining parameters. Through the establishment of the joint surface contact parameters and processing parameters of nonlinear prediction model,which provides a theoretical basis for guiding the selection and optimization of processing technology.
出处
《组合机床与自动化加工技术》
北大核心
2017年第2期130-133,共4页
Modular Machine Tool & Automatic Manufacturing Technique
基金
辽宁省教育厅科学研究一般项目(L2014589)
辽宁省教育厅科学研究一般项目(L2015226)
关键词
深度信念网
结合面
非线性
工艺参数
deep belief network deep
joint surface
nonlinear
process parameters
