论文部分内容阅读
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 the main technical parameter in the machining process, which has a very important influence on the quality of parts and product performance. Taking the relationship between the machined surface roughness and the cutting three factors as the object, the orthogonal test was used to make the cold-working die steel Cr12Mo V with dry cutting by using the cubic boron nitride cutting tool. The surface roughness was processed and the prediction model of the machined surface roughness was established by artificial intelligence neural network. The results show that the prediction model has a good prediction accuracy, and its maximum error does not exceed 5%. The model can predict the surface roughness after machining under the combination of different cutting speed, feed rate and depth of cut. It is of great significance for the selection of cutting dosage and the control of the surface quality of parts in the case of dry hard turning.