基于GA-BP神经网络的矿用刮板输送机故障诊断

针对矿用刮板输送机的故障诊断问题,提出一种基于GA-BP神经网络的故障诊断方法.为了避免BP神经网络易陷入局部最小值、隐含层节点数难确定等问题,这里首先根据经验公式缩小隐含层节点数范围,在小范围里寻找最优的隐含层节点数;进而根据遗传算法具有全局寻优的特点,用遗传算法优化BP神经网络训练的初始权值阈值.研究表明经经验公式...

Fault diagnosis of mine scraper conveyor based on GA-BP neural network

Aiming at the fault diagnosis of mining scraper conveyor,a fault diagnosis method based on GA-BP neural network is proposed.In order to avoid the problems of BP neural network being easy to fall into local minimum and difficult to determine the number of hidden layer nodes,we first narrow down the range of hidden layer nodes according to the empirical formula,and find the optimal number of hidden layer nodes in a small range;The genetic algorithm has the characteristics of global optimization.The genetic algorithm is used to optimize the initial weight threshold of BP neural network training.Research shows that after finding the optimal number of hidden layer nodes through empirical formulas,combining genetic algorithm and BP neural network can effectively solve the problems of slow neural network convergence,easy to fall into local minimums,etc.,and improve the drive section of the scraper conveyor.Fault diagnosis accuracy.The effectiveness of the method in this paper is verified by simulation experiments.