基于BP神经网络和D-S证据理论的刀具磨损监测方法

将BP神经网络和D-S证据理论相结合的方法运用于刀具磨损监测中,采用小波包分解法对刀具磨损过程中产生的声发射信号进行特征提取,构建特征向量,利用BP神经网络识别判断刀具磨损状态;通过BP神经网络的输出结果和训练误差计算D-S证据理论的基本概率赋值,并用D-S证据理论对BP神经网络的识别结果进行决策级融合。实验结果表明:该方法避免了神经网络识别时的误诊,提高了整个刀具磨损监测系统识别的准确性和可靠性。

Tool Wear Monitoring Method Based on BP Neural Network and D S Evidence Theory

The method of BP neural network and D-S evidence theory combination was used in tool wear monitoring. The wavelet packet decomposition method was used to extract the acoustic emission signals from the tool wear process, feature vectors was construc-ted and tool wear state was determined using BP neural network. Basic probability assignment of D-S evidence theory was calculated through the output of BP neural network and training error, and level fusion was decided using recognition results of D-S evidence theo-ry to BP neural network. Experimental results show that this method avoids misdiagnosis of neural network and improves recognition ac-curacy and reliability of the tool wear monitoring system.