Fast intelligent decision of operation schemes for construction of intelligent crude oil pipelines
Article Text (Baidu Translation)
-
摘要: 为解决智慧原油管道建设实时优化的难题，从节能降耗和运行安全2个角度出发构建了以能耗和不安全系数最小为优化目标的运行方案智能决策模型；基于差分进化算法，从变异决策变量越界处理方法和离散决策变量变异算子2个算法角度提出了提高优化算法可靠性和优化效率的改进设想；结合算法计算流程和并行计算框架，提出了4种并行计算策略；以近900 km长的仪征-长岭原油管线(仪长线)作为测试管道来验证和进一步分析算法改进设想与并行计算策略。研究结果表明：结合智能决策模型和优化算法的运行方案智能决策方法可在保证管道安全运行的前提下使仪长线的能耗费用下降7.22%，节能效果明显；改进的变异决策变量越界处理方法和用于离散决策变量变异的浮点数圆整变异算子均能提高原油管道运行方案优化结果的可靠性，前者可使优化计算耗时至少缩短一半，后者可使优化计算耗时至少缩短2/3；在不同的计算机配置下，不同并行计算策略的优劣存在一定的差异，而在最优并行计算策略下，在服务器上优化计算耗时从220 s下降为10 s，加速比可达到22倍。可见，综合算法改进设想和并行计算策略的运行方案快速智能决策方法可使优化计算的加速比超过130倍，显著缩短了优化计算耗时，说明了该智能决策方法对于原油管道快速运行优化的有效性。Abstract: To solve the real-time optimization problem during the construction of intelligent crude oil pipelines, an intelligent decision model of operation schemes with the optimization goals of minimizing the energy consumption and unsafe factor was established from the perspectives of energy saving and operational safety. Based on the differential evolution algorithm, the ideas of improving the reliability and optimization efficiency of the optimization algorithm were proposed from the perspectives of algorithms, including from the processing of mutation decision variables beyond bounds and the mutation operator of discrete decision variables. Combined with the algorithm computation process and parallel computing framework, four parallel computing strategies were proposed. The Yizheng-Changling Crude Oil Pipeline (Yichang Pipeline) with a length of about 900 km was used as the tested pipeline to verify and further analyze the algorithm improvement ideas and parallel computing strategies. Research results indicate that the intelligent decision method of operation schemes combining the intelligent decision model and the optimization algorithm can reduce the energy consumption cost of the Yichang Pipeline by 7.22% on the premise of safe operation of the pipeline, and the energy-saving effect is obvious. The improved processing method of mutation decision variables beyond bounds and the mutation operator of discrete decision variables based on the floating-point rounding can improve the reliability of the optimization results of crude oil pipeline operation schemes, and the former can reduce the optimization computation time by at least half, and the latter can reduce the optimization computation time by at least two-thirds. There are some differences in the advantages and disadvantages of different parallel computing strategies for different computer configurations. Under the optimal parallel computing strategy, the optimization computation time on the server reduces from 220 s to 10 s, and the acceleration ratio can reach 22 times. It can be seen that the acceleration ratio of optimization computation can be accelerated by over 130 times by using the fast intelligent decision method of operation schemes combining the algorithm improvement ideas and parallel computing strategies, and the optimization computation time significantly reduces. The above results demonstrate the effectiveness of the intelligent decision method for the fast operation optimization of the crude oil pipeline.
-
图 1 原油管网结构中的2类长度
Figure 1. Two types of lengths in crude oil pipeline network structure
图 6 不同种群大小下的能耗费用优化结果
Figure 6. Energy consumption cost optimization results under different population sizes
图 8 边界值处理方法下的能耗费用优化结果
Figure 8. Energy consumption cost optimization results under processing method of boundary value
图 9 边界值处理方法下的计算耗时
Figure 9. Computation costs under processing method of boundary value
图 10 随机数处理方法下的能耗费用优化结果
Figure 10. Energy consumption cost optimization results under processing method of random number
图 11 随机数处理方法下的计算耗时
Figure 11. Computation costs under processing method of random number
图 12 不同离散变量变异算子下的能耗费用优化结果
Figure 12. Energy consumption cost optimization results under different mutation operators of discrete variables
图 13 不同离散变量变异算子下的计算耗时
Figure 13. Computation costs under different mutation operators of discrete variables
-
[1] 吴长春, 左丽丽. 关于中国智慧管道发展的认识与思考[J]. 油气储运, 2020, 39(4): 361-370. https://www.cnki.com.cn/Article/CJFDTOTAL-YQCY202004002.htmWU Chang-chun, ZUO Li-li. Understanding and thinking on the development of China's intelligent pipeline[J]. Oil and Gas Storage and Transportation, 2020, 39(4): 361-370. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-YQCY202004002.htm [2] 税碧垣, 张栋, 李莉, 等. 智慧管网主要特征与建设构想[J]. 油气储运, 2020, 39(5): 500-505. https://www.cnki.com.cn/Article/CJFDTOTAL-YQCY202005003.htmSHUI Bi-yuan, ZHANG Dong, LI Li, et al. Main characteristics and construction conception of intelligent pipeline network[J]. Oil and Gas Storage and Transportation, 2020, 39(5): 500-505. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-YQCY202005003.htm [3] 左丽丽, 曾春雷, 姜勇, 等. 长呼原油管道月度节能优化方案[J]. 油气储运, 2015, 34(5): 515-518. https://www.cnki.com.cn/Article/CJFDTOTAL-YQCY201505013.htmZUO Li-li, ZENG Chun-lei, JIANG Yong, et al. Program for optimization of monthly energy preservation in the Changqing-Hohhot Crude Oil Pipeline[J]. Oil and Gas Storage and Transportation, 2015, 34(5): 515-518. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-YQCY201505013.htm [4] ZHOU Ming, ZHANG Yu, JIN Shi-jiu. Dynamic optimization of heated oil pipeline operation using PSO-DE algorithm[J]. Measurement, 2015, 59: 344-351. doi: 10.1016/j.measurement.2014.09.071 [5] 吕梦芸. 基于模拟退火-蚁群算法的原油管道顺序输送运行优化模型[J]. 油气储运, 2017, 36(10): 1154-1161. https://www.cnki.com.cn/Article/CJFDTOTAL-YQCY201710009.htmLYU Meng-yun. The operation optimization model of crude oil batch transportation pipeline based on the simulated annealing-ant colony algorithm[J]. Oil and Gas Storage and Transportation, 2017, 36(10): 1154-1161. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-YQCY201710009.htm [6] BEKIBAYEV T, ZHAPBASBAYEV U, RAMAZANOVA G. Optimal regimes of heavy oil transportation through a heated pipeline[J]. Journal of Process Control, 2022, 115: 27-35. doi: 10.1016/j.jprocont.2022.04.020 [7] 王军防, 矫捷, 余红梅, 等. 基于群体智能优化的原油管道系统能耗优化方法[J]. 油气储运, 2022, 41(11): 1269-1276. https://www.cnki.com.cn/Article/CJFDTOTAL-YQCY202211004.htmWANG Jun-fang, JIAO Jie, YU Hong-mei, et al. Optimization method for energy consumption of crude oil pipeline systems based on swarm intelligence optimization[J]. Oil and Gas Storage and Transportation, 2022, 41(11): 1269-1276. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-YQCY202211004.htm [8] YUAN Qing, CHEN Zhi-min, WANG Xin-ran, et al. Investigation and improvement of intelligent evolutionary algorithms for the energy cost optimization of an industry crude oil pipeline system[J]. Engineering Optimization, 2023, 55(5): 856-875. doi: 10.1080/0305215X.2022.2044805 [9] YUAN Qing, GAO Yu-yao, LUO Yi-yang, et al. Study on the optimal operation scheme of a heated oil pipeline system under complex industrial conditions[J]. Energy, 2023(272): 127139. [10] 王森, 马志鹏, 李善综, 等. 梯级水库群优化调度并行动态规划方法[J]. 中国农村水利水电, 2017(11): 204-207. doi: 10.3969/j.issn.1007-2284.2017.11.043WANG Sen, MA Zhi-peng, LI Shan-zong, et al. Parallel dynamic programming for the optimal operation of cascaded reservoirs[J]. China Rural Water and Hydropower, 2017(11): 204-207. (in Chinese) doi: 10.3969/j.issn.1007-2284.2017.11.043 [11] 纪昌明, 马皓宇, 李传刚, 等. 基于可行域搜索映射的并行动态规划[J]. 水利学报, 2018, 49(6): 649-661. https://www.cnki.com.cn/Article/CJFDTOTAL-SLXB201806001.htmJI Chang-ming, MA Hao-yu, LI Chuan-gang, et al. Research on parallel dynamic programming based on feasible region search mapping[J]. Journal of Hydraulic Engineering, 2018, 49(6): 649-661. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-SLXB201806001.htm [12] 蒋志强, 纪昌明, 孙平, 等. 多层嵌套动态规划并行算法在梯级水库优化调度中的应用[J]. 中国农村水利水电, 2014(9): 70-75. https://www.cnki.com.cn/Article/CJFDTOTAL-ZNSD201409018.htmJIANG Zhi-qiang, JI Chang-ming, SUN Ping, et al. The application of multilayer nested parallel dynamic programming algorithm in cascade reservoirs operation optimization[J]. China Rural Water and Hydropower, 2014(9): 70-75. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-ZNSD201409018.htm [13] 左丽丽, 戴材炜, 赵思睿, 等. 分枝定界法与内点法耦合的含环路输气管网运行优化[J]. 油气储运, 2023, 42(3): 343-351. https://www.cnki.com.cn/Article/CJFDTOTAL-YQCY202303013.htmZUO Li-li, DAI Cai-wei, ZHAO Si-rui, et al. Optimization on operation of gas pipeline network with cyclic structures by coupling branch-and-bound method with interior point method[J]. Oil and Gas Storage and Transportation, 2023, 42(3): 343-351. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-YQCY202303013.htm [14] HERRERA F, LOZANO M, VERDEGAY J L. Tackling real-coded genetic algorithms: operators and tools for behavioural analysis[J]. Artificial Intelligence Review, 1998, 12: 265-319. doi: 10.1023/A:1006504901164 [15] KENNEDY J, EBERHART R. Particle swarm optimization[C]// IEEE. Proceedings of IEEE International Conference on Neural Networks. New York: IEEE, 1995: 1942-1948. [16] STORN R, PRICE K. Differential evolution-a simple and efficient heuristic for global optimization over continuous spaces[J]. Journal of Global Optimization, 1997, 11(4): 341-359. doi: 10.1023/A:1008202821328 [17] WU Xia, LI Chang-jun, HE Yu-fa, et al. Operation optimization of natural gas transmission pipelines based on stochastic optimization algorithms: a review[J]. Mathematical Problems in Engineering, 2018, 2018: 1-18. [18] 王森, 马志鹏, 李善综, 等. 梯级水库群优化调度并行自适应混沌整体退火遗传算法[J]. 人民珠江, 2016, 37(2): 88-91. https://www.cnki.com.cn/Article/CJFDTOTAL-RMZJ201602020.htmWANG Sen, MA Zhi-peng, LI Shan-zong, et al. Parallel self-adaptive chaos whole annealing genetic algorithm for optimal operation of cascaded reservoirs[J]. Pearl River, 2016, 37(2): 88-91. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-RMZJ201602020.htm [19] 王森, 马志鹏, 李善综, 等. 基于Fork/Join多核并行框架的梯级水库群优化调度[J]. 水利水电科技进展, 2017, 37(2): 48-54. https://www.cnki.com.cn/Article/CJFDTOTAL-SLSD201702009.htmWANG Sen, MA Zhi-peng, LI Shan-zong, et al. Optimal operation of cascaded reservoirs based on Fork/Join multi-core parallel framework[J]. Advances in Science and Technology of Water Resources, 2017, 37(2): 48-54. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-SLSD201702009.htm [20] LI Bo, HE Miao, KANG Yang, et al. A hybrid meta-heuristic solution to operation optimization of hot oil pipeline[C]// IEEE. IOP Conference Series: Materials Science and Engineering. New York: IEEE, 2019: 1-10. [21] ZHANG Hai-fei, GE Hong-wei, YANG Jie-ming, et al. Combining affinity propagation with differential evolution for three-echelon logistics distribution optimization[J]. Applied Soft Computing, 2022, 131: 109787. [22] 吴长春, 严大凡. 热油管道稳态运行的两级递阶优化模型[J]. 石油学报, 1989, 10(3): 109-117. https://www.cnki.com.cn/Article/CJFDTOTAL-SYXB198903011.htmWU Chang-chun, YAN Da-fan. A two-level hierarchical model for optimizing steady operation of hot oil pipelines[J]. Acta Petrolei Sinica, 1989, 10(3): 109-117. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-SYXB198903011.htm [23] 吴长春, 李东风, 赵忠德. 秦京管道稳态优化运行方案的分析与确定[J]. 油气储运, 2002, 21(12): 4-11. https://www.cnki.com.cn/Article/CJFDTOTAL-YQCY200212001.htmWU Chang-chun, LI Dong-feng, ZHAO Zhong-de. Steady operational optimization of Qinhuangdao to Beijing Hot Oil Pipeline[J]. Oil and Gas Storage and Transportation, 2002, 21(12): 4-11. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-YQCY200212001.htm [24] VESTERSTROM J, THOMSEN R. A comparative study of differential evolution, particle swarm optimization, and evolutionary algorithms on numerical benchmark problems[C]// IEEE. Proceedings of the 2004 Congress on Evolutionary Computation. New York: IEEE, 2004: 1980-1987. [25] DEB A, ROY J S, GUPTA B. Performance comparison of differential evolution, particle swarm optimization and genetic algorithm in the design of circularly polarized microstrip antennas[J]. IEEE Transactions on Antennas and Propagation, 2014, 62(8): 3920-3928. [26] CHARALAMPAKIS A E, TSIATAS G C. Critical evaluation of metaheuristic algorithms for weight minimization of truss structures[J]. Frontiers in Built Environment, 2019, DOI: 10.3389/fbuil.2019.00113. [27] NANDI S, REDDY M J. Comparative performance evaluation of self-adaptive differential evolution with GA, SCE and DE algorithms for the automatic calibration of a computationally intensive distributed hydrological model[J]. H2 Open Journal, 2020, 3(1): 306-327. [28] BREST J, GREINER S, BOSKOVIC B, et al. Self-adapting control parameters in differential evolution: a comparative study on numerical benchmark problems[J]. IEEE Transactions on Evolutionary Computation, 2006, 10(6): 646-657. [29] 袁庆, 杨洋, 侯昊, 等. 含蜡原油双结构参数模型参数回归的稳定性[J]. 油气储运, 2018, 37(3): 269-275. https://www.cnki.com.cn/Article/CJFDTOTAL-YQCY201803005.htmYUAN Qing, YANG Yang, HOU Hao, et al. The stability of parameter regression for double-structural-parameters model of waxy crude oil[J]. Oil and Gas Storage and Transportation, 2018, 37(3): 269-275. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-YQCY201803005.htm [30] YUAN Qing, LIU Hong-fei, LI Jing-fa, et al. Study on the parametric regression of a multiparameter thixotropic model for waxy crude oil[J]. Energy and Fuels, 2018, 32(4): 5020-5032. [31] 郑帅, 王子涵, 赵浩然, 等. 基于差分进化算法的飞机油量传感器布局优化方法[J]. 航空学报, 2022, 43(8): 125809. https://www.cnki.com.cn/Article/CJFDTOTAL-HKXB202208018.htmZHENG Shuai, WANG Zi-han, ZHAO Hao-ran, et al. Layout optimization method of aircraft fuel gauging sensor based on differential evolution algorithm[J]. Acta Aeronautica et Astronautica Sinica, 2022, 43(8): 125809. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-HKXB202208018.htm [32] ZOU De-xuan, GAO Li-qun, LI S, et al. Solving 0-1 knapsack problem by a novel global harmony search algorithm[J]. Applied Soft Computing, 2011, 11(2): 1556-1564. http://d.wanfangdata.com.cn/periodical/38abf987df6bfded0c7ff44df47568a5 [33] HE Xing-shi, HAN Lin. A novel binary differential evolution algorithm based on artificial immune system[C]//IEEE. 2007 IEEE Congress on Evolutionary Computation. New York: IEEE, 2007: 2267-2272. [34] 孔祥勇, 高立群, 欧阳海滨, 等. 无参数变异的二进制差分进化算法[J]. 东北大学学报(自然科学版), 2014, 35(4): 484-488. https://www.cnki.com.cn/Article/CJFDTOTAL-DBDX201404007.htmKONG Xiang-yong, GAO Li-qun, OUYANG Hai-bin, et al. Binary differential evolution algorithm based on parameterless mutation strategy[J]. Journal of Northeastern University (Natural Science), 2014, 35(4): 484-488. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-DBDX201404007.htm [35] 王森, 马志鹏, 李善综, 等. 粗粒度并行自适应混合粒子群算法及其在梯级水库群优化调度中的应用[J]. 长江科学院院报, 2017, 34(7): 149-154. https://www.cnki.com.cn/Article/CJFDTOTAL-CJKB201707032.htmWANG Sen, MA Zhi-peng, LI Shan-zong, et al. Coarse-grained parallel adaptive hybrid particle swarm optimization algorithm and its application to optimal operation of cascaded reservoirs[J]. Journal of Yangtze River Scientific Research Institute, 2017, 34(7): 149-154. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-CJKB201707032.htm -
下载:
点击查看大图
图(14)
计量
- 文章访问数: 426
- HTML全文浏览量: 111
- PDF下载量: 77
- 被引次数: 0
