【摘要】 用转子振动试验台模拟了汽轮机典型故障,根据其频域变化特性,采用小波包分析对其建立频域能量特征向量,并根据最佳分解树进行了特征选择。最后用神经网络进行故障状态识别,取得了良好的效果。更多还原

【Abstract】 Experimental platform is used to simulate typical faults of turbine. Based on the frequency domain feature, energy eigenvector of frequency domain is presented using wavelet packet analysis method, and the way of best tree is used to choose symptom. The fault states are recognized using neural network. The simulations show that it makes good performance.更多还原