BP神经网络在城市燃气管道剩余寿命预测优化

摘要

针对城市燃气管道布局复杂、影响因素众多的特点, 作者提出基于BP神经网络模型的统计模型对城市燃气管道进行剩余寿命预测, 用差值模型修正BP神经网络模型预测值.实验结果表明: 针对城市燃气管道剩余寿命的预测, BP神经网络模型的统计模型具有很好的预测能力和较佳的推广能力, 验证了构建的基于BP神经网络的时间序列预测模型的有效性和普遍适用性.%Considering the complexity of urban gas pipeline layout and many influential factors, the model BP neural network was used to predict the residual life of the urban gas pipeline, and the predictive value of BP neural network model was modified by the difference model. The experimental results showed that, for the prediction of the remaining life of urban gas pipelines, the predictive ability and generalization ability of the statistical model based on BP neural network model were ideal, the validity and universality of the time series prediction model based on BP neural network were verified.