【摘要】 在多层前向神经网络模型的研究基础上，提出了基于张量的增强型前向神经网络诊断模型，以实现在已知输入模式不变的情况下，增强原始模式的表达，从而提高了诊断的精度。试验结果表明，本模型对工程应用具有较高的实用价值。更多还原

【Abstract】 A new expansional enhanced feed forward neural network model for fault diagnosis of rotating machinery was further provided in this paper, based on studying a conventional back--propagation diagnostic neuralnetwork. This improved approach to fault diagnosis considerably extends the network’S capability for representingcomplex nonlinear relationships between the types of faults and symptoms,promotes the diagnostic accuracy byadding a number of functional units in the input layer. The experimental results show the effectively practical values for engineering applications.更多还原