摘要
采用基于神经网络的重要性权值调整的粒子滤波算法对预处理后的振动信号进行降噪、小波包能量谱提取,将提取到的能量谱作为特征向量用BP神经网络对其进行故障模式分类识别。对经过粒子滤波降噪的数据和没有经过处理的数据分别用BP神经网络进行诊断,之后进行训练、测试和诊断。结果表明经过粒子滤波降噪后的数据诊断效果比较好,也证明了基于神经网络粒子滤波降噪的效果较好。
Using the particle filter algorithm based on the importance of the neural network weights adjustment to do the vibration signal de-noising;Then, extract the wavelet packet energy spectrum;Last, use the energy spectrum as the BP neural network feature vectors classification and identification of failure modes. A particle filter noise reduction data and processed data were used to BP neural network to diagnose. After the training, testing and diagnosis,the results suggest that, after the diagnosis of denoised data is better,and also proved that a neural network-based particle filter in noise reduction is better.
出处
《煤矿机械》
北大核心
2013年第5期301-303,共3页
Coal Mine Machinery
关键词
柴油机
故障诊断
粒子滤波
神经网络
diesel engine
fault diagnosis
particle filter
neural network