论文部分内容阅读
为解决深孔加工中表面粗糙度在线检测困难这一问题,提出一种基于BP神经网络的表面粗糙度在线辨识方法,并以BTA钻削为例,建立表面粗糙度BP神经网络在线辨识模型,并将其引入钻削加工领域。该模型能方便地预测钻削加工参数对加工表面粗糙度的影响,有助于准确认识已加工表面质量随切削参数的变化规律,为切削参数的优选和表面粗糙度的控制提供了依据。实验和仿真结果表明,基于BP神经网络模型能够很好地预测表面粗糙度,对提高加工表面粗糙度具有一定的指导意义。
In order to solve the problem of on-line surface roughness detection in deep hole machining, an on-line surface roughness identification method based on BP neural network is proposed. Taking BTA drilling as an example, an on-line identification model of surface roughness BP neural network is established, And introduce it into the field of drilling. The model can easily predict the influence of drilling parameters on the machined surface roughness, and help to know accurately the changing rule of the machined surface quality with the cutting parameters, which provides the basis for optimizing the cutting parameters and controlling the surface roughness. The experimental and simulation results show that the BP neural network model can predict the surface roughness well, which is of guiding significance to improve the surface roughness.