论文部分内容阅读
提出一种结合小波包分解和模糊神经网络的故障诊断方法,采用小波包分解与重构提取各频带的能量作为故障特征向量,并以此为学习样本,再利用正交最小二乘学习算法训练模糊神经网络,确定故障诊断系统模型,对轴承故障进行诊断和识别.仿真结果及与其它一些方法比较表明:该轴承故障诊断方法可以有效识别和预测轴承的状态,且学习效率、准确性和可靠性等方面均有较大提高.
A fault diagnosis method based on wavelet packet decomposition and fuzzy neural network is proposed. The wavelet packet decomposition and reconstruction are used to extract the energy of each frequency band as the fault eigenvector, which is used as a learning sample and trained by orthogonal least squares algorithm Fuzzy neural network to determine the fault diagnosis system model to diagnose and identify the bearing faults.The simulation results and comparison with other methods show that the bearing fault diagnosis method can effectively identify and predict the bearing status and learning efficiency, accuracy and reliability Sexual and other aspects have greatly improved.