本文介绍了BP网络的原理、算法,并用BP网络对采煤机截割部机械传动系统的故障进行了趋势预测。经过地面模拟加载实验及井下验证,证明用人工神经网络可较好地预报机器故障,变被动维修为视情维修,为合理安排生产计划及设备检修提供了可靠的依据。 This paper introduces the principle and algorithm of BP network and predicts the trend of mechanical transmission system fault in shearer cutting department by BP network. Through the simulation test of the ground and the verification of the underground, it is proved that the artificial neural network can predict the fault of the machine better, change the passive maintenance as the condition maintenance, and provide the reliable basis for arranging production planning and equipment overhaul reasonably.