所属单位：

管理学院

发表刊物：

2010 Second ETP/IITA World Congress in Applied Computing,Computer Science,and Computer Engineering

关键字：

中文关键字：天然气管道；BP神经网络；状态预测，英文关键字：gas pipeline, BP neutral network, state prediction

摘要：

Predictive maintenance is an important part of risk management in the fields of natural gas transmission. This paper introduces an effective, real-time, predictive maintenance system based on the artificial neutral network. The aim of the proposed system is to localize and detect normal operational conditions in order to predict mechanical abnormalities lead to the failure of the pipeline. The most common three-phase BP neutral network is taken as the research object, which selects a lot of maintenance sample to train by means of BP neutral network, predicts equipment state and failure time in the future. Training the external coating detecting data of a city, the calculation result shows that it is effective to predict maintenance state of gas pipeline by BP neutral network. Considering the character of gas pipeline underground, BP model is more effective and will be widely used in thermal explosion study.

备注：

张志霞

第一作者：

张艳,张志霞

论文类型：

期刊论文

卷号：

卷：

期号：

期：

页面范围：

页：

是否译文：

否

发表时间：

2010-04-01