磨削智能预测控制系统研究

建立了一种智能预测控制系统。该系统根据各磨削阶段的特点，在不同阶段分别采用不同的优化控制策略：粗磨阶段，采用在烧伤极限内大进给和变速磨削优化策略；精磨阶段，采用由神经网络预测、模糊逻辑控制的工件尺寸智能优化方法；光磨阶段，采用工件表面粗糙度模糊神经网络预测辨识控制方法。基于神经网络的专家系统，提供各阶段初始磨削加工参数。实验结果表明，该系统在外圆磨削加工中适应性强，可极大地提高磨削质量和效率。

Study of Intelligent Prediction Control System in Grinding

An intelligent prediction control system was built. Optimization control strategy was changed in the different grinding stage. Deep -feed within the limit of burn and variety velocity grinding were adopted during the rough grinding stage; the prediction neural network and the fuzzy logic controller was used to optimize and control the workpiece size during the fine grinding stage; two fuzzy - neural networks were used to predict and control workpiece surface roughness during spark - out stage. The expert system based on neural network provides the initial grinding parameters for these grinding stages. Experimental results show that this intelligent pre diction control system is feasible and has high adaptive capability.