针对刀具磨损声发射信号的非平稳特征和BP神经网络学习算法收敛速度慢、易陷入局部极小值等问题,提出了基于经验模态分解和最小二乘支持向量机的刀具磨损状态识别方法.首先对声发射信号进行经验模态分解,将其分解为若干个固有模态函数之和,然后分别对每一个固有模态函数进行自回归建模,最后提取每一个自回归模型的系数组成特征向量,特征向量被分为两组,一组用于对最小二乘支持向量机训练,另一组用于识别刀具磨损状态.试验结果表明:该方法能很好地识别刀具磨损状态,与BP神经网络相比具有更高的识别率. In view of the non-stationary characteristics of acoustic emission signal of tool wear and the slow convergence rate of BP neural network learning algorithm and the tendency to fall into local minima, the method of tool wear state recognition based on empirical mode decomposition and least square support vector machine is proposed. Firstly, the AE signal is decomposed into the sum of several intrinsic mode functions, and then the autoregressive modeling of each intrinsic mode function is carried out. Finally, the coefficients of each autoregressive model are extracted The vectors and eigenvectors are divided into two groups, one for training LSSVM and the other for identifying the tool wear state.The experimental results show that this method can identify the tool wear state well, Neural networks have higher recognition rates.