文章检索
首页» 过刊浏览» 2019» Vol.4» Issue(3) 310-322     DOI : 10.3969/j.issn.2096-1693.2019.03.028
最新目录| | 过刊浏览| 高级检索
基于多种智能算法的腐蚀天然气管道可靠性评价方法
何蕾,温凯,吴长春,宫敬*
中国石油大学( 北京) 机械与储运工程学院,北京 102249
A corroded natural gas pipeline reliability evaluation method based on multiple intelligent algorithms
HE Lei, WEN Kai, WU Changchun, GONG Jing
College of Mechanical and Transportation Engineering, China University of Petroleum-Beijing, Beijing 102249, China

全文:   HTML (1 KB) 
文章导读  
摘要  天然气管道地理环境复杂、运行工况多变,以蒙特卡罗模拟为代表的不确定性仿真是目前腐蚀管道可靠性评价的主要方法。然而天然气管道高设计可靠度特性所带来的高次模拟问题,使蒙特卡罗模拟十分耗时。为解决这一问题,本文采用神经网络算法取代蒙特卡罗模拟的可靠性评价方法,建立管道基本参数与可靠度的非线性模型。针对目前神经网络算法应用过程中存在的先验信息与神经网络模型的融合问题,本文创新性地提出智能优化算法与神经网络算法相结合的方法。该方法能够将腐蚀管道可靠度变化规律融入到建模过程中。建立了从特征变量的选择、样本数据的生成与处理、神经网络模型构建及模型预测效果评价一体化计算流程。在多种工况下采用神经网络模型对管道结构可靠度进行预测,结果表明该模型能够在极短的时间内获得与蒙特卡罗模拟高度近似的评价结果。相比于传统的神经网络模型,该方法建立的模型在可靠度预测准确性及可靠度变化规律的反映能力方面均有大幅度提高。
服务
把本文推荐给朋友
加入我的书架
加入引用管理器
关键词 : 腐蚀天然气管道;可靠性;人工神经网络建模方法改进;模拟退火算法;拉丁超立方抽样;遗传算法
Abstract

Natural gas pipelines have complex geographical environments and varied operating conditions. Uncertainty simulation represented by Monte Carlo methods has become the main method for pipeline corrosion reliability assessment. However,the high-order simulation problems caused by the high design reliability of natural gas pipelines make Monte Carlo simulations very time-consuming. In order to solve this problem, this paper uses a neural network algorithm rather than Monte Carlo simulation to establish a nonlinear model of basic pipeline parameters and reliability. Because of the difficulty of combining prior information in the modeling process, this paper proposes an innovative method that combines an intelligent optimization algorithm and a neural network algorithm. This method can incorporate the pipe corrosion reliability variation into the modeling process. An integrated computational flow from the selection of feature variables, the generation and processing of sample data,the construction of neural network models and the evaluation of model prediction effects are proposed. Under various working conditions, the neural network model constructed by the method proposed in this paper predicts the reliability of pipeline structures. The results show that the model can obtain the calculation results highly similar to Monte Carlo simulation in a very short time. Compared with the traditional neural network model, the model established by this method has greatly improved the reliability of prediction and the ability to reflect changes in reliability.

Key words: corroded gas pipelines; reliability; artificial neural network modeling method improvement; simulated annealing algorithm; Latin hypercube sampling; genetic algorithm
收稿日期: 2019-09-29     
PACS:    
基金资助:国家自然科学基金青年基金资助项目“基于状态空间模型的天然气管网瞬态优化控制研究”(51504271) 资助
通讯作者: ydgj@cup.edu.cn
引用本文:   
何蕾, 温凯, 吴长春, 宫敬. 基于多种智能算法的腐蚀天然气管道可靠性评价方法. 石油科学通报, 2019, 03: 310-322
链接本文:  
HE Lei, WEN Kai, WU Changchun, GONG Jing. A corroded natural gas pipeline reliability evaluation method based on multiple intelligent algorithms. Petroleum Science Bulletin, 2019, 03: 310-322.
版权所有 2016 《石油科学通报》杂志社