基于连续高斯密度混合HMM的刀具磨损状态监测

针对端面铣刀磨损状态的识别问题,根据隐式马尔可夫模型(HMM)具有良好的模式分类能力,提出了基于连续高斯密度混合HMM(CHMM)的刀具磨损状态监测系统.以铣削力作为监测信号,应用小波包理论对铣削力信号进行分析和消噪处理,并提取信号的能量特征作为CHMM的输入向量,训练CHMM模型,再用训练好的模型对未知的刀具磨损状态进行监测与识别,实验结果表明该模型可以对刀具磨损状态进行准确的识别,且所需训练样本数较少,对刀具状态的智能监测具有很好的实际意义.

Tool Wear Condition Monitoring Based on Continuous Gaussian Mixture HMM

Aiming at the problem of the identification of cutting tool wear condition,and according to the merit of Hidden Markov Model (HMM) with perfect classifying ability,the system of the tool wear condition monitoring based on continuous Gaussian mixture HMM (CHMM) was presented.With the milling force as the monitoring signal,the wavelet package theory was adopted to analyze and de-noise the milling force signal,and extracts energy feature of the signal as import vectors of CHMM,trains CHMM.Then the unknown stat...