石油化工高等学校学报

石油化工高等学校学报 ›› 2017, Vol. 30 ›› Issue (5): 80-85.DOI: 10.3969/j.issn.1006-396X.2017.05.015

• 油气储运 • 上一篇    下一篇

基于支持向量机-CV的天然气水合物生成预测

宫清君,马贵阳,潘 振,刘培胜,李存磊   

  1. (辽宁石油化工大学石油与天然气工程学院,辽宁抚顺113001)
  • 收稿日期:2017-02-06 修回日期:2017-02-28 出版日期:2017-10-31 发布日期:2017-11-10
  • 通讯作者: 潘振(1981-),男,博士,副教授,从事油气储运方面研究;E-mail:28335719@qq.com
  • 作者简介:宫清君(1986-),男,硕士研究生,从事天然气水合物研究;E-mail:1449611564@qq.com。
  • 基金资助:
    国家自然科学基金项目(41502100);辽宁省高等学校优秀人才支持计划项目(LJQ2014038)。

Prediction of Natural Gas Hydrate Formation Based on Support Vector Machine (SVM)CV

  1. (Petroleum and Natural Gas Engineering,Liaoning Shihua University,Fushun Liaoning 113001,China)
  • Received:2017-02-06 Revised:2017-02-28 Published:2017-10-31 Online:2017-11-10

摘要: 天然气水合物的生成过程是一个多组分、多物态的系统,存在着复杂的结晶成核过程,需要考虑压力、温度、促进剂、搅拌速度等因素的影响,不但涉及动力学问题还涉及热力学问题,对其生成很难进行精确预测。基于支持向量机理论,结合实验数据,建立支持向量机预测模型来进行天然气水合物生成时的相平衡压力预测,采用平均平方误差、平方相关系数,以及平方绝对百分比误差和平均绝对误差等四种误差公式对预测精度进行评估, 结果分别为8.37008×10-5、99.8976%、0.5424%、1.9900%,还对源数据进行了归一化([1,2])预处理以及利用交叉验证方法对核参数g(4)和惩罚因子c(1.4142)进行了优化。模拟结果显示,由支持向量机预测模型得到的相平衡压力与实际实验获得的相平衡压力基本一致,预测效果较理想,证明该模型具有较高的准确性和可靠性。

关键词: 天然气水合物,     ,  结晶,    ,  成核,    ,  热力学,    ,  支持向量机,    , 交叉验证

Abstract: Natural gas hydrate has the advantages of abundant reserves, large calorific value and low emission, which can mitigate the environmental pollution problems caused by traditional fossil energy. The generation process of natural gas hydrate form is a system with multicomponents and multiphysical states. The nucleation process is complex, which needs to consider the effects of pressure, temperature, promoters, stirring speed and so on. It is difficult to accurately predict the hydrate formation, because the hydrate formation process not only involves thermodynamics problems but also dynamics problems. In our paper, the support vector machine theory combined with experimental data was used to establish support vector machine prediction model for predicting natural gas hydrate equilibrium pressure. The prediction accuracy was estimated by using the mean square error, the square correlation coefficient, the square absolute percentage error and the average absolute error. The results are 8.370 08×10-5,99.897 6%,0.542 4%,1.990 0%,respectively. The pretreatment origin data were normalized ([1,2]) and the nuclear parameter g(4)and punishment factor c(1.414 2) were optimized by using cross validation methods. Simulation results show that the equilibrium pressure obtained by support vector prediction model is good in agreement with the equilibrium obtained by experiments. The better ideal prediction effects prove that the model has advantages of accuracy and reliability. It can provide certain reference for research on natural gas hydrate in future.

Key words: Natural gas hydrate,    ,  Nucleation,    ,  Dynamics,    ,  Thermodynamics,    ,  Support vector machine,    ,  Cross validation

引用本文

宫清君,马贵阳,潘 振,刘培胜,李存磊. 基于支持向量机-CV的天然气水合物生成预测[J]. 石油化工高等学校学报, 2017, 30(5): 80-85.

Gong Qingjun,Ma Guiyang,Pan Zhen,et al. Prediction of Natural Gas Hydrate Formation Based on Support Vector Machine (SVM)CV[J]. Journal of Petrochemical Universities, 2017, 30(5): 80-85.

使用本文