论文部分内容阅读
对BP神经网络在齿轮故障诊断中的模式表达、网络拓扑及其相关参数等问题进行了探讨;并利用BP 网络对齿轮四种典型的故障模式进行训练学习和诊断,取得了满意的效果.结果表明:BP 神经网络是实时地解决齿轮故障中复杂的状态识别问题的一种有效工具“,”This paper presents artificial neural netwirk\'s essential principles and its features. The questions of model representations,BP model structures and relative parameters in the gear fault diagnosis are discussed. By using classical BP neural network, four kinds of typical pattems of gear faults have been studied and diagnosed and satisfied results have been acquired. The research results indicate that BP neural network with the excellent abilities of parallel distributed processing, self study, self adaptation, self organization, associative memory and its highly non linear pattern recognition is an efficient and feasible tool to solve complicated state identification problems in the gear fault diagnosis simultaneously.