基于人工智能算法的深水钻井平台最优航行路径研究  

Research on Optimal Navigation Path of Deepwater Drilling Platform Based on Artificial Intelligence

作　　者：袁俊亮 Yuan Junliang(CNOOC Research Institute Co.,Ltd,Beijing 100028,China)

机构地区：[1]中海油研究总院有限责任公司,北京100028

出　　处：《科技通报》2022年第5期68-71,共4页Bulletin of Science and Technology

基　　金：国家科技重大专项海洋深水油气田开发工程技术(三期)(2016ZX05028)。

摘　　要：深水油气勘探开发过程中,钻井平台的井间航行效率是影响开发经济性的关键,针对深水钻井的特殊作业工序,研究钻井平台最优航行路径,明确目标函数为平台由初始位置出发,依次进行各井表层批钻作业,沿同路径逆序返回完成下部钻完井作业,最终到达指定结束位置的总路径长度。基于人工智能模拟退火算法,通过引入随机变量,以一定概率得到更劣解的代价跳出局部最优解,换取全局最优解。方法具有较强鲁棒性,Python程序实现后进行深水钻井平台航行路线规划,能以最优的路径节省航行工期和燃料成本。通过实际算例,验证了方法的可行性。In the process of deep-water oil and gas exploration and development, the efficiency of drilling platform navigation between wells is the key to the economic efficiency of development. For the special operation procedures of deep-water drilling, the optimal navigation path of the drilling platform is studied, and the objective function is that the platform starts from the initial position and proceeds in sequence. In batch drilling operations on the surface of each well, return along the same path in reverse order to complete the bottom drilling and completion operations, and finally reach the total path length of the designated end position. Based on the simulated annealing algorithm, through the introduction of random variables, the local optimal solution is jumped out at the cost of getting a worse solution with a certain probability, in exchange for the global optimal solution. The method has strong robustness. The calculated results of Python programming are used in the navigation route planning of the deepwater drilling platform, which can save the navigation period and fuel cost with the optimal route. Through actual calculation examples, the feasibility of the method is verified.

关 键 词：人工智能 模拟退火 海洋油气 深水钻井 最优路径 

分 类 号：TE52[石油与天然气工程—油气田开发工程]