当前位置: X-MOL 学术Appl. Soft Comput. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Modeling and coordinated optimization method featuring coupling relationship among subsystems for improving safety and efficiency of drilling process
Applied Soft Computing ( IF 7.2 ) Pub Date : 2020-11-18 , DOI: 10.1016/j.asoc.2020.106899
Yang Zhou , Xin Chen , Min Wu , Weihua Cao

Drilling is an important means of obtaining resources. Since the complicated bottom hole conditions and coupling relationship among subsystems, it is difficult to accurately predict the drilling states and simultaneously improve drilling efficiency and safety. A novel modeling and coordinated optimization method has been developed to solve that. In the modeling part, based on the analysis of the correlation between subsystems, two online support vector regression (OSVR) models are established to predict drilling states of rate of penetration (ROP) and mud pit volume (MPV) respectively. In the optimization part, based on the prediction models, the problem of how to improve drilling efficiency and safety is described into a two-objective optimization issue, which includes improving ROP and maintaining MPV at same time. Then a coordinated optimization strategy is developed to finish it, which adopts the nondominated sorting genetic algorithm II (NSGA-II) to find out pareto set, and the technique for order preference by similarity to an ideal solution (TOPSIS) method to determine the final optimal operating parameters. Finally, the verification of modeling and coordinated optimization method based on the actual drilling data show that it can improve ROP by an average of 39.8% and reduce the fluctuation of the MPV by an average of 69.3%, which demonstrates effectiveness and practicability for our method.



中文翻译:

具有子系统间耦合关系的建模和协调优化方法,以提高钻井过程的安全性和效率

钻探是获得资源的重要手段。由于复杂的井底条件和子系统之间的耦合关系,因此难以准确地预测钻井状态并同时提高钻井效率和安全性。为了解决这个问题,已经开发了一种新颖的建模和协同优化方法。在建模部分中,基于对子系统之间相关性的分析,建立了两个在线支持向量回归(OSVR)模型,分别预测钻速的钻速,钻速(ROP)和矿坑体积(MPV)。在优化部分中,基于预测模型,将如何提高钻井效率和安全性的问题描述为两个目标的优化问题,包括同时提高ROP和维持MPV。然后开发了一种协调优化策略以完成该策略,该策略采用非主导排序遗传算法II(NSGA-II)找出pareto集,并通过与理想解决方案(TOPSIS)方法相似的顺序偏好技术来确定最终结果。最佳运行参数。最后,基于实际钻井数据的建模与协调优化方法的验证表明,该方法可以平均提高ROP 39.8%,降低MPV波动平均69.3%,证明了该方法的有效性和实用性。 。通过类似于理想解决方案(TOPSIS)方法的顺序偏好技术来确定最终的最佳操作参数。最后,基于实际钻井数据的建模与协调优化方法的验证表明,该方法可以平均提高ROP 39.8%,降低MPV波动平均69.3%,证明了该方法的有效性和实用性。 。通过类似于理想解决方案(TOPSIS)方法的顺序偏好技术来确定最终的最佳操作参数。最后,基于实际钻井数据的建模与协调优化方法的验证表明,该方法可以平均提高ROP 39.8%,降低MPV波动平均69.3%,证明了该方法的有效性和实用性。 。

更新日期:2020-11-18
down
wechat
bug