摘要
地面站发生故障后,故障诊断对于其快速恢复有重大意义。文章使用BP神经网络对地面站故障进行诊断,针对BP神经网络易陷入局部极值点提出了遗传算法优化神经网络的方法,在训练过程中使用遗传算法结合BP神经网络避免网络收敛过早。结果表明优化后的神经网络故障诊断精度提高,减小了故障诊断的不确定性。
Fault diagnosis is of great significance for quick recovery of ground station failure. In this paper, BP neural network is used to diagnose the fault of the ground station; In view that the BP neural network is easy to fall into the local extreme point, genetic algorithm is put forward to optimize the neural network. Genetic algorithm and BP neural network are used to avoid premature convergence of network in the training process. The results show that the fault diagnosis accuracy of optimized neural network is improved, and the uncertainty of fault diagnosis is reduced.
出处
《信息工程大学学报》
2017年第2期140-142,共3页
Journal of Information Engineering University
基金
国家自然科学基金资助项目(61501513)
关键词
地面站
故障诊断
BP神经网络
遗传算法
ground station
fault diagnosis
BP neural network
genetic algorithm
