【作者】 周兆忠； 李兴林； 李欣；

【Author】 ZHOU Zhaozhong;LI Xinglin;LI Xin;Department of Mechanical Engineering,Zhejiang University;Hangzhou Bearing Test&Research Center;College of Mechanical Engineering,Quzhou University;

【机构】 浙江大学机械工程学系； 杭州轴承试验研究中心有限公司； 衢州学院机械工程学院；

【摘要】 精密孔镗削加工过程中极易出现的颤振,往往会导致精密孔的表面质量下降,影响机械装备的可靠性。预报控制可在形成颤振纹之前对颤振进行快速抑制,避免颤振对工件的损害,是最为有效的颤振抑制方法之一。快速、准确的识别出颤振发生的征兆是镗削颤振预报及控制的重要环节。为此,本文提出了基于隐马尔科夫模型(HMM)的镗削颤振识别预报方法,以实现对镗削颤振征兆的快速识别预报。该方法首先根据颤振信号的时频特点,利用频谱分析等手段对镗削振动信号进行分析处理,提取出反映颤振征兆的特征向量,并输入HMM模型中与训练得到的模式库进行相似概率推算,实现镗削状态的快速识别分类。实验结果表明,利用HMM对镗削颤振进行识别预报,可以快速识别分离出镗削颤振征兆,颤振识别准确率可达94%,为后续的颤振抑制环节提供基础,从而有效提高精密孔的表面加工质量,提高产品可靠性。更多还原

【Abstract】 Chatter often occurs during the precision hole boring processing,and it results in low quality of finished surface,damages the reliability of mechanical equipment.Prediction control is the most effective chatter suppression method,which can suppress chatter rapidly to prevent damage to the surface of precision hole.This paper aims to solve the problem by establishing time series model of vibration acceleration signal in boring process based on Hidden Markov Model(HMM) technology and achieve the purpose of chatter recognition and prediction.Features which can indicate boring states are extracted from the vibration signal.HMM parameters are obtained by model training,and the reference models database is built.Then boring state recognition is performed according to the feature matching level.Simulations and experiments are conducted,and the results show that the proposed method is feasible and it could get high recognition accuracy.更多还原