基于GA-BP神经网络的电梯门系统故障预测

Faults Forecast of the Elevator Door System Based on GA-BP Neural Network

将遗传算法（GA）运用于反向传播（BP）神经网络算法建立预测模型，对电梯门系统故障进行预测，避免了BP神经网络权值和阈值的随机性对预测结果产生的误差。介绍了利用该预测模型进行电梯门系统故障预测的具体方法，通过Matlab软件仿真表明，该预测模型具有可行性。

The back-propagation （BP） neural network algorithm with the genetic algorithm （GA） are applied to establish the prediction model of the fault of elevator door system, the error of prediction results is avoided, which caused by the randomness of BP neural network weights and thresholds. The method of using the model to predict the fault of elevator door system is introduced. The simulation results by Matlab software show that the model is feasible.