基于小波包能量谱的HMM钻头磨损监测

Drill Wear Monitoring by Using Hidden Markov Model(HMM) Based on Wavelet Packets Energy Spectrum

从工程应用的角度论述了小波包分解原理及其能量谱监测理论,并将该理论应用于钻削力信号特征提取中,针对钻削过程特征矢量与钻头磨损之间具有较强的随机性和不确定性的特点,提出一种基于隐马尔可夫模型(HMM)的钻头磨损监测方法。实验结果表明,通过对钻削力信号进行多层小波包分解,提取各频段能量谱作为特征矢量可准确刻画工艺系统随钻头磨损的演化规律,利用HMM建立的各钻头磨损状态小波包能量谱的统计模型可有效跟踪钻头磨损的发展趋势,实现钻头磨损状态和寿命的监测。

From an angle of engineering application, this paper dealt with the wavelet packets decomposition principle and its energy spectrum monitoring theory, which were used to extract the fea tures of drilling force signals. Meanwhile, with an aim at the strong randomization and uncertainty characteristics between the feature vectors and drill wears in drilling process, a kind of drill wear monitoring method based on Hidden Markov Model（HMM） was presented. The experimental results in dicate that the energy spectrum feature vectors of the drilling force signals extracted from multi-layer wavelet packets decomposition can accurately portray the evolution laws of technological system with drill wears, and that the statistics model for the wavelet packets energy spectrum of each drill wear condition can be established by using HMM,which can effectively track the developing trends of drill wears so as to realize the monitoring of drill wear states and tool life.