基于支持向量机的刀具磨损决策融合技术

摘要

Decision fusion method based on support vector machine is proposed for the limitations of com-monly used Bayesian algorithms and D-S evidence theory. Tool wear condition monitoring system capable of real-time monitoring signal vibration and acoustic emission signals in the turning process was established. The Decision fusion is achieved using support vector machine, based on BP and Elman neural network rec-ognition signal. Experimental results show that decision fusion method based on support vector machine has a good recognition rate and robustness. At the same time, this approach saves time than single neural net-work, online monitoring of the cutting tool wear state is more easy to implement.%针对常用的贝叶斯算法和D-S证据论的局限性提出了基于支持向量机( SVM)的决策融合方法。建立了能够实时监测车削加工过程中振动和声发射信号的刀具磨损状态监测系统，在对分析信号进行BP和Elman神经网络识别的基础上，利用支持向量机实现了决策融合。实验结果证明，基于支持向量机的决策融合方法具有良好的识别率和鲁棒性，且比单用某一种网络节省时间，更有利于实现切削加工刀具状态的在线监测。