该文利用神经网络聚类学习方法对机械故障的故障模式进行识别分类，通过实验研究，证明该方法作为一种新的自适应模式识别技术，比传统的聚类方法和基于ＢＰ神经网络故障模式识别方法具有较高的模式分类能力。图１表６参９ In this paper, neural network clustering learning method is used to identify and classify the failure modes of mechanical failure. Experimental studies show that the proposed method is a new adaptive pattern recognition technology, which is more efficient than traditional clustering methods and fault modes based on BP neural network Identification method has a high ability of pattern classification. Figure 1 Table 6 参 9