期刊文献+

基于改进型SVM算法的气液两相流持液率计算模型 被引量:1

Liquid Holdup Calculation Model of Gas-Liquid Two-Phase Flow Based on Improved SVM Algorithm
下载PDF
导出
摘要 气液两相流持液率的精准计算对于流型识别、管道腐蚀评价与预测以及输气管道输送效率计算等方面的研究具有重要的意义。目前,国内外专家学者建立的持液率计算模型适应范围有限,缺乏一套适应于不同工况条件的持液率计算模型。本文首先统计分析了国内外不同专家学者共2123组实验研究数据,构建了丰富的室内实验数据库;再选定支持向量机(SVM)对数据进行训练和回归预测,为了提高算法的可靠性,采用K-交叉验证(K-CV)、遗传算法(GA)以及粒子群优化算法(PSO)对SVM算法的惩罚因子c和核函数参数g寻优过程进行优化,分别建立了K-CV-SVM、GA-SVM、PSO-SVM模型,综合考虑计算精度和稳定性,最终优选了GA-SVM作为持液率计算模型的核心算法。将该模型与Eaton、BB、MB、BBE等经验关系式模型进行了计算精度对比分析,结果显示:建立的持液率计算模型在上倾管、水平管以及下倾管中都具有比经典模型更佳的计算精度。本文基于GA-SVM算法建立的持液率计算模型计算精度高、稳定性强、适应性广泛,可满足不同工况条件下持液率计算的需求。 The accurate calculation of liquid holdup of gas-liquid two-phase flow is of great significance for the research of two-phase flow pattern identification,pipeline corrosion evaluation and prediction,and the calculation of transmission efficiency of gas transmission pipeline.At present,the liquid holdup calculation models established by experts and scholars at home and abroad have limited scope of application,and there is a lack of a set of liquid holdup calculation model suitable for different working conditions.Firstly,this paper statistically analyzes 2123 groups of experimental research data from different experts and scholars at home and abroad,and constructs a rich indoor experimental database.Then,the data are trained and predicted using support vector machine(SVM).In order to improve the reliability of the algorithm,the optimization process of the penalty factor C and kernel function parameter g of SVM algorithm is optimized using K-cross validation(K-CV),genetic algorithm(GA)and particle swarm optimization(PSO)separately,and K-CV-SVM,GA-SVM and PSO-SVM models are established respectively.Taking into account the calculation accuracy and stability of algorithm,GA-SVM model is selected for the liquid holdup calculation of gas-liquid two-phase flow.The calculation accuracy of the model is compared with that of the empirical relationship models such as Eaton,BB,MB and BBE.The results show that the established liquid holdup calculation model has higher calculation accuracy than the classical models for upward inclined pipe,horizontal pipe and downward inclined pipe.The liquid holdup calculation model based on GA-SVM algorithm has high calculation accuracy,strong stability and wide adaptability,which can meet the needs of liquid holdup calculation under different working conditions.
作者 花靖 蒋秀 于超 谷成林 靳彦欣 逄铭玉 HUA Jing;JIANG Xiu;YU Chao;GU Chenglin;JIN Yanxin;PANG Mingyu(Qingdao Safety Engineering Research Institute,SINOPEC,Qingdao,Shandong 266071,China)
出处 《西安石油大学学报(自然科学版)》 CAS 北大核心 2022年第6期103-110,118,共9页 Journal of Xi’an Shiyou University(Natural Science Edition)
基金 国家青年科学基金项目“油气混输管道水合物沉积与剥离脱落机理研究”(51904330)。
关键词 气液两相流 持液率 管道腐蚀评价与预测 计算模型 支持向量机 K-交叉验证 遗传算法 粒子群算法 gas-liquid two-phase flow liquid holdup pipeline corrosion evaluation and prediction calculation model SVM K-CV GA PSO
  • 相关文献

参考文献13

二级参考文献129

共引文献620

同被引文献15

引证文献1

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部