Dynamic Optimization-Based Intelligent Control System for Drilling Rate of Penetration (ROP): Simulation and Industrial Application

Optimization control of the rate of penetration (ROP) is crucial due to its vital role in maximizing the drilling efficiency. In this article, a dynamic optimization-based intelligent control system for drilling ROP is proposed considering the drilling characteristics. First of all, the framework of...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on industrial informatics 2024-03, Vol.20 (3), p.1-8
Main Authors: Gan, Chao, Cao, Wei-Hua, Liu, Kang-Zhi, Wu, Min
Format: Article
Language:English
Subjects:
Algorithms
Artificial neural networks
Automation
Constraint modelling
Control systems
Controllability
Drilling
Drilling process
Dynamic models
dynamic optimization
Heuristic algorithms
industrial application
Industrial applications
Informatics
Intelligent control
Machine learning
Mathematical models
Optimization
Predictive models
Process control
rate of penetration (ROP)
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Optimization control of the rate of penetration (ROP) is crucial due to its vital role in maximizing the drilling efficiency. In this article, a dynamic optimization-based intelligent control system for drilling ROP is proposed considering the drilling characteristics. First of all, the framework of the proposed system is described, which has two layers (intelligent optimization layer and basic automation layer). In the former layer, two stages (ROP modeling stage and ROP optimization/implementation stage) are executed alternatively by using the moving window strategy. Moving window-Extreme learning machine and tenfold cross validation are used to establish the dynamic model between the rotation speed (RPM), weight on bit (WOB), depth, and ROP. In addition, hybrid bat algorithm is introduced to search the controllable parameters while the inputs for ROP optimization are RPM, WOB, depth, constraints, and ROP model, and the outputs are the optimized RPM and optimized WOB. After that, the outputs are recommended to the driller to be used as the setpoints of the basic automation layer. Comparison results of simulation with seven well-known methods demonstrate the effectiveness of the proposed system. In addition, in an industrial application to a real-world drilling process in the Xiangyang area, Central China, the ROP was improved by 15.9%.
ISSN:1551-3203
1941-0050
DOI:10.1109/TII.2023.3313633