摘要
表面粗糙度是机械加工工艺中主要的技术参数,对零件质量和产品性能有着极为重要的影响。以加工表面粗糙度与切削用量三要素的关系为对象,采用正交试验方法,利用立方氮化硼刀具对冷作模具钢Cr12Mo V进行硬态干式车削试验,测量得到选定参数条件下的加工表面粗糙度值,并应用人工智能神经网络方法建立了加工表面粗糙度预测模型。结果表明,该预测模型具有很好的预测精度,其最大误差不超过5%。模型可以对不同切削速度、进给量和切削深度参数组合下加工后的表面粗糙度进行预测,对干式硬车条件下的切削用量选择和零件表面质量的控制具有重要指导意义。
Surface roughness is a main technical index in machining. It has significant influence on the quality of machined parts and the performance of products. This paper addresses the relations between the machined surface roughness and the three cutting regimes. Using orthogonal experiment method, hard dry cutting experiments for cold work die steel Cr12MoV were conducted with cubic boron nitride cutting tools. Based on the measured surface roughness values under different parameters, a model for forecasting surface roughness in turning was established using Artificial Neural Network. Results show that the prediction model has excellent precision, and the maximum prediction error is less than 5%. The model can predict surface roughness values of machined parts under different combinations of cutting speed, feed rate, and depth of cut. The study will provide guidance for the selection of cutting parameters and the control of surface quality in hard dry turning conditions.
出处
《机械设计与研究》
CSCD
北大核心
2016年第1期96-99,共4页
Machine Design And Research
关键词
干式硬车
立方氮化硼刀具
正交试验
神经网络
智能预测
hard dry turning
CBN cutting tool
orthogonal experiment
artificial neural network
intelligent prediction
