研究了人工神经网络的原理、结构和学习算法,并将该网络应用于带式输送机滚动轴承的故障诊断中。采集不同类型的滚动轴承故障信号,并对信号进行预处理。利用神经网络进行训练,当训练误差满足设定要求时,训练完成。利用训练成熟的神经网络对滚动轴承进行故障诊断。实验结果表明神经网络技术可以快速、准确地诊断出带式输送机滚动轴承的故障类型。 The principle, structure and learning algorithm of artificial neural network are studied, and the network is applied to the fault diagnosis of the belt conveyor rolling bearing. Different types of rolling bearing fault signal acquisition, and signal pre-processing. Training using neural network, when the training error to meet the set requirements, the training is completed. Use the trained neural network to carry on the breakdown diagnosis to the rolling bearing. The experimental results show that neural network technology can quickly and accurately diagnose the fault type of the belt conveyor rolling bearing.