工件表面粗糙度计算机预报平台设计

Platform Design on Surface Roughness Prediction of High Speed Machining

构建了基于工控机的工件表面粗糙度预报硬件平台,完成了自动检测和预报软件的分析与设计,核心部分采用神经网络进行建模,提出利用神经网络进行高速铣削表面粗糙度预报的方法,给出了具体的网络实现过程,应用灵敏度剪枝算法克服了网络隐层难以确定的问题,仿真结果表明该方法的有效性,对高速加工切削参数的选择和表面质量控制具有指导意义。

The prediction platform constructed by industrial computer and the measuring software is designed.The artificial neural networks with new algorithm is the core design.It is applied into prediction models for surface roughness of high speed machining.Sensitivity pruning algorithm is applied to resolve the problem that the hidden layer nodes of neural networks are hard to determine.Simulation shows the method is effective and can provide a guidance to optimize cutting param-eters and control surface quality.