您的位置:山东大学 -> 科技期刊社 -> 《山东大学学报(工学版)》

山东大学学报 (工学版) ›› 2024, Vol. 54 ›› Issue (4): 42-50.doi: 10.6040/j.issn.1672-3961.0.2023.111

• 机器学习与数据挖掘 • 上一篇    

基于改进多目标粒子群算法的储气库注气优化

杜睿山1,2,井远光1,孟令东2,张豪鹏1   

  1. 1.东北石油大学计算机与信息技术学院, 黑龙江 大庆 163318;2.油气藏及地下储库完整性评价黑龙江省重点实验室(东北石油大学), 黑龙江 大庆 163318
  • 发布日期:2024-08-20
  • 作者简介:杜睿山(1977—),男,黑龙江大庆人,副教授,硕士生导师,硕士,主要研究方向为人工智能与智能优化. E-mail:ruishan_du@163.com
  • 基金资助:
    黑龙江省自然科学基金资助项目(LH2021F004)

Optimization of gas storage based on improved multi-objective particle swarm optimization algorithm

DU Ruishan1,2, JING Yuanguang1, MENG Lingdong2, ZHANG Haopeng1   

  1. 1. Department of Computer and Information Technology, Northeast Petroleum University, Daqing 163318, Heilongjiang, China;
    2. Key Laboratory of Oil and Gas Reservoir and Underground Gas Storage Integrity Evaluation(Northeast Petroleum University), Daqing 163318, Heilongjiang, China
  • Published:2024-08-20

摘要: 为减少储气库不合理注气导致的微震次数,保证储气库注气量最大,构建基于双向长短期记忆(bi-directional long short-term memory, BiLSTM)神经网络预测代理模型,降低微震次数和储气库有效应力的预测误差,提出一种精英进化多目标粒子群优化(elite-evolved multi-objective particle swarm optimizer, EMPSO)算法。采用基于排序分组策略对种群进行分组,并在每个分组内进行随机精英竞争学习,提高算法的多样性;引入精英聚集的思想,加快算法的收敛速度。基于BiLSTM模型和EMPSO算法对储气库注气过程进行优化,与其他3种多目标优化算法进行对比,将EMPSO算法应用于实际配产优化。结果表明,改进后的算法具有更好的Pareto前沿、更快的收敛速度,优化后微震次数和有效应力分别降低了9.78%和10.12%,对保障储气库安全和提高储气库储气量具有重要意义。

关键词: 地下储气库, 代理模型, 双向长短期记忆, 改进的粒子群算法, 多目标寻优

中图分类号: 

  • TP391
[1] 黄晟, 王静宇, 郭沛, 等. 碳中和目标下能源结构优化的近期策略与远期展望[J]. 化工进展, 2022, 41(11): 5695-5708. HUANG Sheng, WANG Jingyu, GUO Pei, et al. Short-term strategy and long-term prospect of energy structure optimization under carbon neutrality target[J]. Chemical Industry and Engineering Progress, 2022, 41(11): 5695-5708.
[2] 仝少凯, 高德利. 波动注入水力压裂诱发微地震的力学机制及其对压裂效果的影响[J]. 石油钻采工艺, 2020, 42(1): 98-113. TONG Shaokai, GAO Deli. Mechanical principles of the fluctuation injection based hydraulic fracturing to induce microseismic and its influence on the fracturing effect[J]. Oil Drilling & Production Technology, 2020, 42(1): 98-113.
[3] 刘佳宁, 刘得军, 钱步仁, 等. 基于NSGA_Ⅱ的地下储气库注气节能优化运营研究[J]. 天然气工业, 2017, 37(1): 160-166. LIU Jianing, LIU Dejun, QIAN Buren, et al. Optimization of energy-saving operation in underground gas storage injection based on NSGA_Ⅱ[J]. Natural Gas Industry, 2017, 37(1): 160-166.
[4] 徐帅, 张青庆, 李小明, 等. 金坛盐穴储气库注采运行参数优化设计研究[J]. 石油钻采工艺, 2020, 42(4): 490-496. XU Shuai, ZHANG Qingqing, LI Xiaoming, et al. Optimization design of injection/production parameters of Jintan salt-cavern gas storage[J]. Oil Drilling & Production Technology, 2020, 42(4): 490-496.
[5] 张浩为, 谢军伟, 张昭建, 等. 基于混合遗传-粒子群算法的相控阵雷达调度方法[J]. 系统工程与电子技术, 2017, 39(9): 1985-1990. ZHANG Haowei, XIE Junwei, ZHANG Zhaojian, et al. Scheduling based on the hybrid genetic particle swarmalgorithm for the phased array radar[J]. Systems Engineering and Electronics, 2017, 39(9): 1985-1990.
[6] YUAN F, LÜ K, TANG B, et al. Optimization design of oil-immersed iron core reactor based on the particle swarm algorithm and thermal network model[J]. Mathematical Problems in Engineering, 2021, 2021: 1-14.
[7] 李猛, 郑得文, 邱小松, 等. 储气库不同类型砂岩储层压敏特征及其影响因素[J]. 石油实验地质, 2023, 45(2): 385-392. LI Meng, ZHENG Dewen, QIU Xiaosong, et al. Stress sensitivity characteristics and influencing factors of different types of sandstone reservoirs in gas storage[J]. Petroleum Geology & Experiment, 2023, 45(2): 385-392.
[8] 杨术刚, 张坤峰, 刘双星, 等. 页岩渗透率测定方法及影响因素研究进展[J/OL]. 油气地质与采收率.(2022-11-07)[2023-06-24]. http://dx.doi.org/10.13673/j.cnki.cn37-1359/te.202204016.
[9] 谢承旺, 余伟伟, 闭应洲, 等. 一种基于分解和协同的高维多目标进化算法[J]. 软件学报, 2020, 31(2): 356-373. XIE Chengwang, YU Weiwei, BI Yingzhou, et al. Many-objective evolutionary algorithm based on decomposition and coevolution[J]. Journal of Software, 2020, 31(2): 356-373.
[10] KENNEDY J, EBERHART R. Particle swarm optimization[C] //Proceedings of ICNN'95-International Conference on Neural Networks. Perth, Australia: IEEE, 1995: 1942-1948.
[11] 徐杰, 周新志. 基于边界自适应技术的精英交互学习粒子群算法[J/OL]. 计算机科学.(2023-05-15)[2023-06-24]. http://kns.cnki.net/kcms/detail/50.1075.TP.20230512.1409.002.html.
[12] 陈强, 蔡琦盼, 邓博仁. 基于改进混沌粒子群优化算法的永磁同步电机参数辨识[J]. 传感器与微系统, 2023, 42(4): 157-160. CHEN Qiang, CAI Qipan, DENG Boren. Parameter identification of PMSM based on improvedchaos PSO algorithm[J]. Transducer and Microsystem Technologies, 2023, 42(4): 157-160.
[13] 孙鸿昌, 周风余, 单明珠, 等. 基于模式划分的空调能耗混合填补方法[J]. 山东大学学报(工学版), 2022, 52(1): 9-18. SUN Hongchang, ZHOU Fengyu, SHAN Mingzhu, et al. Mode division based hybrid filling method of air conditioning energy consumption[J]. Journal of Shandong University(Engineering Science), 2022, 52(1): 9-18.
[14] 孙东磊, 鉴庆之, 李智琦, 等. 源网协调的电力系统均匀性规划[J]. 山东大学学报(工学版), 2022, 52(5): 92-101. SUN Donglei, JIAN Qingzhi, LI Zhiqi, et al. Power system uniformity planning based on source network coordination[J]. Journal of Shandong University(Engineering Science), 2022, 52(5): 92-101.
[15] 张伟, 黄卫民. 基于种群分区的多策略自适应多目标粒子群算法[J]. 自动化学报, 2022, 48(10): 2585-2599. ZHANG Wei, HUANG Weimin. Multi-strategy adaptive multi-objective particle swarm optimization algorithm based on swarm partition[J]. Acta Automatica Sinica, 2022, 48(10): 2585-2599.
[16] KESHTEGAR B, KOLAHCHI R. Reliability analysis-based conjugate map of beams reinforced by ZnO nanoparticles using sinusoidal shear deformation theory[J]. Steel and Composite Structures, 2018, 28(2): 195-207.
[17] KESHTEGAR B. Chaotic conjugate stability transfor-mation method for structural reliability analysis[J]. Computer Methods in Applied Mechanics and Engineering, 2016, 310: 866-885.
[18] MENG Z, LI G, YANG D, et al. A new directional stability transformation method of chaos control for first order reliability analysis[J]. Structural and Multidisci-plinary Optimization, 2017, 55: 601-612.
[19] ZITZLER E, LAUMANNS M, THIELE L. SPEA2: improving the strength Pareto evolutionary algorithm[J]. TIK-Report, 2001, 103: 5-10.
[20] 王成宇, 林名驰, 唐政. 基于属性频率和精度的组合预测单项模型筛选[J]. 统计与决策, 2022, 38(5): 22-27. WANG Chengyu, LIN Mingchi, TANG Zheng. Bootstrap interval estimation for unknown autocorrelation process capability index[J]. Statistics and Decision, 2022, 38(5): 22-27.
[21] ALSHAMMARI M E, RAMLI M A M, MEHEDI I M. An elitist multi-objective particle swarm optimization algorithm for sustainable dynamic economic emission dispatch integrating wind farms[J]. Sustainability, 2020, 12(18): 7253.
[22] 宣涛, 高丽军, 秦鹏, 等. 海上废弃气藏改建地下储气库可行性:以琼东南盆地H气田为例[J]. 天然气地球科学, 2022, 33(2): 324-332. XUAN Tao, GAO Lijun, QIN Peng, et al. Feasibility of rebuilding abandoned offshore gas reservoir into underground gas storage: case study of H gas field in Qiongdongnan Basin[J]. Natural Gas Geoscience, 2022, 33(2): 324-332.
[1] 李源,张妮,张艳娜,刘士豪,李学辉. 用于预测边界元弱奇异积分的新型樽海鞘-神经网络模型[J]. 山东大学学报 (工学版), 2023, 53(6): 8-15.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!