This paper investigated the relationships between the features of the cutting force signal and tool wear in time and frequency domain. The kurtosis coefficient and the energy of special frequency range of cutting force signal were taken as the signal features of tool wear as well as the peak value coefficient, then the vectors constituted of the signal features were inputted to artificial neural network for fusion in order to realize brainpower identification of tool wear. The experimental results show that this method possesses high identity precision and powerful extending ability.%从时域、频域提取了切削力信号特征参数随着刀具磨损量增加的变化规律,提取了切削力信号的峰值因子、Kurtosis系数和频段带能量作为刀具磨损量监测特征参数,并将各个特征量构成的特征矢量输入改进的多层反传神经网络进行融合,实现钻削过程刀具磨损量的智能识别。试验结果表明,该方法具有较高的识别精度和较强的抗干扰能力。
展开▼