摘要
根据刀具磨损状态不同时其不同频带的能量不同,将小波包分解方法和基于神经网络的模糊系统融合器相结合,用于车刀状态诊断。采用小波包将信号分解为不同频带的信号,通过求取不同频带的均方根值提取各特征量,然后将特征向量分别输入BP、SVM、ELM、PNN 4种神经网络分类器,将不同分类器的分类结果应用模糊网络进行优化综合。实验结果表明:多分类融合分类识别效果比单个分类器效果要好,提高了对刀具状态的识别精度。
In order to discuss tool wear condition, this paper combines the wavelet packet with fuzzy neural network based on fusion different frequency band signals system to diagnose tool condition. Through decomposing the signal into by using wavelet packet and through calculating the RMS of different frequency bands to extract the characteristic, this paper mainly analyzes the condition of tool wear. Then the present author input characteristics respectively into four neural network classifier that is BP, SVM, EL and PNN, and then put the classification results of different classifiers into practice by using fuzzy network optimization synthesis. The exper/mental results show that the multiple classifier fusion is more effective than a single classifier, which can improve the precision of recognizing cutting tool condition.
出处
《煤矿机械》
北大核心
2014年第2期225-227,共3页
Coal Mine Machinery
关键词
刀具磨损
小波包
特征提取
神经网络分类器
分类器融合
tool wear, wavelet packet
feature extraction
neural network classifier, multiple classifiers fusion
