基于KNN的机床刀尖点频响函数预测

加工颤振是影响工件表面质量、加剧刀具磨损和降低机床寿命的重要原因,颤振抑制一直以来都是学术界和工业界关注的重点。稳定性叶瓣图是现有颤振抑制方法的重要依据,而机床刀尖点频响函数是绘制稳定性叶瓣图的主要输入。锤击试验法是目前获取刀尖模态参数最为准确的方法,但是在机床结构变化频繁的应用场景下,该方法效率低,机床需要长时间停机,难以满足实际生产要求。提出了基于KNN的机床刀尖点频响函数预测方法,将锤击试验法和KNN算法相结合,大幅减小了锤击试验的次数,同时准确获得机床刀尖点频响函数。在试验验证中,将该方法和传统RCSA方法进行对比,结果表明所提方法具有良好的准确度。

KNN-Based Tool Tip Frequency Response Function Prediction Method

Chatter in machining usually results in poor surface finish,reduces the life of machine tools and damage on cutters,and chatter suppression has always been the focus of academia and industry.The stability lobe diagram(SLD)based on the tool tip frequency response function(FRF)is the important basis for the existing chatter suppression methods.The impact test method is the most accurate method for obtaining the tool tip FRF,however,in application scenarios where the structure of the machine tool changes frequently,the efficiency of this method is not satisfactory.Therefore,a KNNbased tool tip FRF prediction method is proposed in this paper,which combines the impact test method with the KNN algorithm,there by greatly reducing the time consumption of the impact test method and accurately obtaining the tool tip FRF.In experimental verification,this method is compared with the RCSA method,and the results show the accuracy of the proposed method.