.png){kind=icon}
.png){kind=icon}
Return
Efficiency-safety coordination optimization in drilling process under complex formations
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2025.129732.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Efficient and safe drilling process under complex formation conditions has significant economic value for drilling engineering. Rate of penetration (ROP) and drill-string vibration are two widely used objectives for optimizing the drilling efficiency and safety, yet a simultaneous optimization of both is still a challenge due to their strong coupling relationship. To address this issue, an artificial intelligence-based coordinated optimization strategy is proposed for real-time dual-objective optimization of the two targets. First, by exploiting the multivariate distribution characteristics of drilling parameters, a Gaussian mixture model is applied for formation identification. Then, an information entropy-based coupling coordination degree (CCD) model is proposed to quantify the coordination relationship, and constrain optimization objectives. Finally, a dual-objective optimization model with ROP and vibration, served as the optimization objectives, is constructed, and adaptive model constraints are designed for different formations. A real-time optimization strategy combining non-dominated sorting genetic algorithm II and sliding window technique is developed to determine optimal operational parameters, and a CCD-based decision criterion is developed for the Pareto solution set. Experiments on industrial data from an actual drilling field indicate that the proposed strategy leads to significant gains in drilling performances, providing a practical solution for drilling engineering.
Keywords:
Coupling coordination degree
Drill-string vibration
Formation identification
Non-dominated sorting genetic algorithm II
Rate of penetration