论文部分内容阅读
建立了4因素5水平的正交试验表,以加工速度和表面粗糙度为目标值进行了镁合金板材电火花线切割加工工艺试验。借助SAS统计分析,获得了镁合金板材线切割加工速度和表面粗糙度模型的多元回归方程,同时获得了镁合金板材线切割加工影响因素的显著性排序,分别为脉冲峰值电流、脉间距和脉宽,工件厚度对镁合金板材线切割加工基本无影响。基于各影响因素的最好水平,优化了工艺参数组合;借助BP神经网络对镁合金板材线切割加工工艺进行了预测,预测值与实际目标值的误差在训练误差范围内,满足要求。
The orthogonal experiment table of 4 factors and 5 levels was set up. The machining speed and surface roughness of the magnesium alloy sheet were tested by WEDM. With the aid of SAS statistical analysis, the multiple regression equations of the wire-cut machining speed and surface roughness of magnesium alloy sheet were obtained, and the significant order of influence factors of wire-cut magnesium alloy sheet were obtained, including pulse peak current, pulse distance and pulse Width, thickness of the workpiece on the magnesium alloy sheet metal cutting basically no effect. Based on the best level of each factor, the process parameters were optimized. The BP neural network was used to predict the wire cutting process of magnesium alloy sheet. The error between the predicted value and the actual target value was within the range of training error to meet the requirements.