基于神经网络的提升机减速器工况预测研究

Research on Condition Predicting of Hoist Reducer Based on Neural Network

针对传统监测方法无法实现提升机减速器工况预测的缺点,利用Matlab神经网络工具箱建立了提升机减速器工况参数的预测模型。对比模型预测值和实际测量值表明:BF和RBF神经网络模型预测结果和实际值的误差均小于10%,证明了神经网络模型用于减速器工况预测的可行性。对比BP和RBF神经网络预测结果,表明RBF神经网络模型训练时间短,预测精度高,更加适用于井下提升机减速器工况参数预测。

For condition monitoring of gear box in elevator can＇t be predicted by traditional methods, the predicting model of gear box in elevator was established with artificial neural network tool box of Matlab.The reducer bearing temperature was predicted through BP and RBF neural network by Matlab. Through contrasting analysis it shows that the RBF neural network has good prediction effect and high application value. A comparison of prediction data with test data indicates that error between them are all less than 10%. And it approves that neural network is feasibility to predicte condition of gear box in elevator. Compare prediction results of BP and RBF neural network, it shows that RBF neural network has short training time, high prediction accuracy and more appropriate for condition prediction of gear box in elevator than BP neural network.