基于支持向量机结合遗传算法的天然气水合物相平衡研究

发布时间：2018-04-01 02:17

本文选题：天然气水合物　切入点：可靠性　出处：《天然气工业》2017年05期

【摘要】：天然气水合物(以下简称水合物)具有高储气率和高可靠性等优点,在天然气储存及运输方面具有广泛的应用前景,同时水合物的存在也会给输气管道带来堵塞等严重影响,因此对水合物的生成研究具有重要意义。为此,对Ⅰ型水合物在无添加剂条件下的静态生成规律进行了研究。首先基于水合物动力学实验装置进行一系列实验,然后利用支持向量机(SVM)结合遗传算法(GA)建立了水合物生成预测模型(SVM+GA)。据此将实验中得到的温度和压力数据进行预测和优化处理,并对上述数据进行非线性拟合,得出了相平衡曲线及其方程,计算得出了常温下生成水合物的相平衡压力为33.5 MPa,常压下生成水合物的相平衡温度为237.1 K。将分别由SVM+GA模型、Chen-Guo模型和vd W-P热力学模型所得到的数据与经典的实验数据进行了对比,其平均相对误差分别为2.678%、1.447%和3.249%。结论认为:SVM+GA模型具有较高的计算准确度,比Chen-Guo模型和vd W-P热力学模型更为简便,可为水合物开发研究提供更多的数据。
[Abstract]:Natural gas hydrate (hereinafter referred to as gas hydrate) has the advantages of high gas storage rate and high reliability, and has a wide application prospect in natural gas storage and transportation. At the same time, the existence of gas hydrate will also cause serious effects on gas transmission pipeline, such as blockage.Therefore, it is of great significance to study the formation of hydrate.For this reason, the static formation of type I hydrate without additives was studied.Firstly, a series of experiments were carried out based on the hydrate kinetics experimental device, and then a prediction model of hydrate formation was established by using support vector machine (SVM) and genetic algorithm (GA).Based on this, the temperature and pressure data obtained from the experiment are predicted and optimized. The phase equilibrium curve and its equation are obtained by nonlinear fitting of the above data.The phase equilibrium pressure of hydrate formation is 33.5 MPA at room temperature and the phase equilibrium temperature of hydrate formation is 237.1 K.The data obtained from the SVM GA model Chen-Guo model and the vd W-P thermodynamic model are compared with the classical experimental data. The average relative errors are 2.678% and 3.249%, respectively.It is concluded that the weight SVM GA model is more accurate than Chen-Guo model and vd W-P thermodynamic model, and can provide more data for hydrate development.
【作者单位】：辽宁石油化工大学石油与天然气工程学院;
【基金】：国家自然科学基金项目(编号:41502100) 辽宁省高等学校优秀人才支持计划项目(编号:LR2013016) 辽宁省自然科学基金项目(编号:201602470)
【分类号】：TE81

【参考文献】