论文部分内容阅读
通过对环型航空零件的薄壁结构及材料的切削加工性能进行分析,结合现场铣削实验确定出刀具磨损对环型航空零件加工精度的影响。结合刀具磨损的研究现状和加工工况,确定选用声发射技术进行监测。结合BP神经网络,运用小波包算法建立刀具磨损监测模型。其识别结果与实际结果的一致性较好,能实时、准确、可靠地监测铣刀的磨损情况。
By analyzing the thin-walled structure of the annular aeronautical components and the machining performance of the materials, the influence of the tool wear on the machining accuracy of the annular aeronautic components is determined by the field milling experiment. Combined with the research status of tool wear and processing conditions, the selection of acoustic emission technology for monitoring. Combined with BP neural network, the tool wear monitoring model is established by using wavelet packet algorithm. Its recognition result is in good agreement with the actual result, which can monitor the milling cutter’s wear status in real time, accurately and reliably.