面向智慧原油管道建设的运行方案快速智能决策  

Fast intelligent decision of operation schemes for construction of intelligent crude oil pipelines

作　　者：王军防 曹旦夫 矫捷 余红梅 袁庆 宇波[3] 陈志敏 邓雅军 WANG Jun-fang;CAO Dan-fu;JIAO Jie;YU Hong-mei;YUAN Qing;YU Bo;CHEN Zhi-min;DENG Ya-jun(PipeChina Network Corporation Eastern Oil Storage and Transportation Co.,Ltd.,Xuzhou 221008,Jiangsu,China;School of Chemical Engineering and Technology,Xi'an Jiaotong University,Xi'an 710049,Shaanxi,China;School of Mechanical Engineering,Beijing Institute of Petrochemical Technology,Beijing 102617,China;School of Energy and Power Engineering,Northeast Electric Power University,Jilin 132012,Jilin,China)

机构地区：[1]国家管网集团东部原油储运有限公司,江苏徐州221008 [2]西安交通大学化学工程与技术学院,陕西西安710049 [3]北京石油化工学院机械工程学院,北京102617 [4]东北电力大学能源与动力工程学院,吉林吉林132012

出　　处：《交通运输工程学报》2023年第5期210-222,共13页Journal of Traffic and Transportation Engineering

基　　金：国家自然科学基金项目(51906018);北京石油化工学院重要科研成果培育项目(BIPTACF-002);北京市教育委员会资金支持项目(22019821001)。

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。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

关 键 词：管道运输 智慧原油管道 智能决策 实时优化 差分进化算法 并行计算 

分 类 号：U171[交通运输工程]