1.中国石油塔里木油田公司 克拉采油气管理区 地面工艺部,新疆 库尔勒 841000
2.中国石油塔里木油田公司 克拉采油气管理区 克深8采气作业区,新疆 库尔勒 841000
3.中国石油塔里木油田公司 克拉采油气管理区 生产办,新疆 库尔勒 841000
梁龙贵(1982—),本科,工程师,研究方向为设备管理和天然气净化处理等,E-mail:cnpc_lianglg@163.com。
扫 描 看 全 文
梁龙贵,张龙,郭仕为等.基于IAO-PNN模型的天然气水合物生成条件预测研究[J].低碳化学与化工,2023,48(06):170-176.
LIANG Longgui,ZHANG Long,GUO Shiwei,et al.Study on prediction of nature gas hydrate formation conditions based on IAO-PNN model[J].Low-carbon Chemistry and Chemical Engineering,2023,48(06):170-176.
梁龙贵,张龙,郭仕为等.基于IAO-PNN模型的天然气水合物生成条件预测研究[J].低碳化学与化工,2023,48(06):170-176. DOI: 10.12434/j.issn.2097-2547.20230008.
LIANG Longgui,ZHANG Long,GUO Shiwei,et al.Study on prediction of nature gas hydrate formation conditions based on IAO-PNN model[J].Low-carbon Chemistry and Chemical Engineering,2023,48(06):170-176. DOI: 10.12434/j.issn.2097-2547.20230008.
为降低流动保障中水合物堵塞导致的问题,收集天然气水合物生成实验数据,构造了概率神经网络(PNN)模型。通过自适应权重和双曲正切函数,对天鹰(AO)算法进行改进,实现了平滑参数的优化,最终建立了基于IAO-PNN的水合物生成条件预测模型。通过与热力学模型及机器学习模型进行比较,验证了算法的优越性。结果表明,AO算法改进后(IAO),寻优精度和收敛速度明显优于AO、粒子群(PSO)和麻雀(SSA)等智能算法;IAO-PNN模型与实验数据的吻合性相对最高,适合二元体系、多元体系、酸性体系和醇盐体系中的水合物生成条件预测,且在高压环境下的预测效果良好;与热力学模型及机器学习模型相比,IAO-PNN模型在训练集上的均方根误差(,RMSE,)为0.6176、决定系数(,R,2,)为0.9994,测试集上的,RMSE,为0.7624、,R,2,为0.9991,表现出良好的泛化性能。通过现场验证,IAO-PNN模型适用性良好,可为现场解堵措施的制定提供参考。
In order to mitigate the issues caused by hydrate blockage in flow assurance, experimental data on natural gas hydrate formation was collected to construct a Probabilistic Neural Network (PNN) model. By improving the Aquila Optimizer (AO) algorithm through adaptive weights and hyperbolic tangent function, optimization of smoothing parameters was achieved, resulting in the establishment of an IAO-PNN-based hydrate formation prediction model. A comparison with thermodynamic models and machine learning models validated the superiority of the algorithm. The results show that the improved AO algorithm (IAO) exhibits significantly higher optimization precision and convergence speed compared to intelligent algorithms such as AO, PSO and SSA. The IAO-PNN model exhibits the highest consistency with experimental data, making it suitable for predicting hydrate formation conditions in binary systems, multicomponent systems, acid systems and alcohol-salt systems, and it demonstrates good predictive performance in high-pressure environments. Compared to thermodynamic models and machine learning models, the IAO-PNN model shows excellent generalization performance, with an root mean square error (,RMSE,) of 0.6176 and an coefficient of determination (,R,2,) of 0.9994 on the training set, and an ,RMSE, of 0.7624 and an ,R,2, of 0.9991 on the test set. Through on-site verification, the IAO-PNN model displays good applicability and can provide reference for formulating on-site remediation measures.
IAO-PNN模型天然气水合物热力学模型机器学习
IAO-PNN modelnatural gashydratethermodynamic modelmachine learning
赵甜, 寇丽颖, 高红松, 等. 凝析气集输管道中天然气水合物冻堵防控措施效果模拟[J]. 油气田地面工程, 2021, 40(10): 11-16.
姚海元, 陈海宏, 伍壮, 等. 深水油气田流动安全保障技术研究进展[J]. 海洋工程装备与技术, 2022, 9(3): 73-78.
樊镇, 都凯, 贺艳祥, 等. 海上天然气水合物降压开采气液管柱设计及优化研究[J]. 中国海上油气, 2022, 34(6): 157-167.
郭平, 冉文博, 刘煌. 天然气水合物生成条件预测研究进展[J]. 科学技术与工程, 2018, 18(29): 133-139.
王海秀. 天然气管道水合物生成预测模型研究进展[J]. 应用化工, 2016, 45(11): 2173-2177.
马贵阳, 宫清君, 潘振, 等. 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[J]. 天然气工业, 2017, 37(5): 46-52.
卞小强, 韩兵, 杜志敏. 基于支持向量机的酸性天然气水合物生成条件预测[J]. 中国科技论文, 2016, 11(9): 1017-1020.
徐小虎, 方惠军, 王创业, 等. 含抑制剂体系下天然气水合物形成预测模型的建立与应用[J]. 天然气化工—C1化学与化工, 2022, 47(1): 130-137+147.
李恩, 刘云, 吴森林, 等. 基于ISCA-BP算法的天然气水合物预测模型[J]. 化学工程, 2022, 50(8): 62-67.
张新生, 杨青. 基于GMM-PNN模型的海底油气管道风险等级评价[J]. 安全与环境学报, 2021, 21(3): 935-942.
赵妍, 赵起, 张劲松, 等. 改进PNN神经网络在电力系统次/超同步振荡监测中的应用[J]. 电力电容器与无功补偿, 2022, 43(5): 76-83.
朱正林, 张冕. 基于AO优化VMD-CE-BiGRU的光伏发电功率预测[J]. 国外电子测量技术, 2022, 41(10): 56-61.
陈烨, 闫铁, 孙晓峰, 等. 基于Multiflash的天然气水合物相平衡影响因素及规律[J]. 成都理工大学学报(自然科学版), 2020, 47(3): 358-366.
陈烨, 闫铁, 孙晓峰, 等. 水合物热力学抑制剂性能评价及变化规律数值模拟研究[J]. 石油与天然气化工, 2020, 49(2): 42-46+53.
刘唯一, 陈勇, 王淼, 等. 盐类对甲烷水合物稳定性影响研究进展[J]. 岩矿测试, 2018, 37(2): 111-120.
余丹. 基于数据驱动的水合物生成预测研究[D]. 北京: 中国石油大学(北京), 2019.
GHIASI M M. Initial estimation of hydrate formation temperature ofsweet natural gases based on new empirical correlation [J]. J Nat Gas Chem, 2012, 21(5): 508-512.
BALLARD A L, SLOAN J E D. The next generation of hydrate prediction: I. Hydrate standard states and incorporation of spectroscopy [J]. Fluid Phase Equilib, 2002, 194(197): 371-383.
NIXDORF J, OELLRICH L R. Experimental determination of hydrate equilibrium conditions for pure gases, binary andternary mixtures and natural gases [J]. Fluid Phase Equilib, 1997, 139(1/2): 325-333.
NG H J, ROBINSON D B. The measurement and prediction of hydrate formation in liquid hydrocarbon-water systems [J]. Ind Eng Chem Res, 1976, 15(4): 293-298.
NASRIFAR K, MOSHFEGHIAN M. A model for prediction of gas hydrate formation conditions in aqueous solutions containing electrolytes and/or alcohol [J]. J Chem Thermodyn, 2001, 33(9): 999-1014.
JOHN V T, PAPADOPOULOS K D, HOLDER K D. A generalized model forpredicting equilibrium conditions for gas hydrates [J]. AIChE J, 1985, 31(2): 252-259.
SUN C Y, CHEN G J, LIN A W, et al. Hydrate formation conditions of sour natural gases [J]. J Chem Eng Data, 2003, 48(3): 600-602.
NG H J, ROBINSON D B. Hydrate formation in systems containing methane, ethane, propane, carbon dioxide or hydrogen sulfide in the presence of methanol [J]. Fluid Phase Equilib, 1985, 21(1/2): 145-155.
宋琦. 多元复杂体系水合物生成的实验及热动力学模型研究[D]. 江苏: 常州大学, 2010.
LU Z Q, SULTAN N, JIN C S, et al. Semiquantitative analysis of factorsaffecting gas hydrate formation conditions and its fractions [J]. Chin J Geophys, 2008, 51(1): 97-104.
MOHAMMADI A H, KRAOUTI I, RICHON D. Methane hydrate phaseequilibrium in the presence of NaBr, KBr, CaBr2, K2CO3 and MgCl2 aqueous solutions: Experimental measurements and predictions ofdissociation conditions [J]. J Chem Thermodyn, 2009, 41(6): 779-782.
YANG M J, SONG Y C, LIU Y, et al. Influence of pore size, salinity andgas composition upon the hydrate formation conditions [J]. Chin J Chem Eng, 2010, 18(2): 292-296.
徐亦凤, 刘升, 刘宇凇, 等. 融合差分变异和切线飞行的天鹰优化器[J]. 计算机应用研究, 2022, 39(10): 2996-3002.
CHEN G J, GUO T M. Thermodynamic modeling of hydrate formation based on new concepts [J]. Fluid Phase Equilib, 1996, 122(1): 43-65.
DU Y, GUO T M. Prediction of hydrate formation for systems containing methanol [J]. Chem Eng Sci, 1990, 45(4): 893-900.
0
浏览量
0
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构