Filling the Experience gap in the Drilling Optimization Continuous Improvement Cycle through a Self-Learning Expert System

Author:

Kirby Cliff1,Sadlier Andreas1,Wood Christopher1,Vinther Morten2

Affiliation:

1. Baker Hughes

2. Verdande Technology

Abstract

Abstract With deeper and more complex wells being drilled every year to gain access to reserves, experience and knowledge are the keys for minimizing associated risks and reducing costly non-productive time. Over the last decade, drilling optimization processes and practices have delivered substantial drilling improvements in many different environments worldwide. This has been based on a continuous improvement cycle, consisting of four distinct phases: planning, execution, post-well analysis and lessons learned, which essentially yields personnel experience and knowledge. Given the current demographics in the oil industry, which is heavily biased towards the 50+ years of age, the "big crew change" is just around the corner. As more and more graduate engineers enter the industry the resulting experience gap needs to be bridged. Within the controlled environment of the office, graduate engineers are offered guidance and support during the planning phase, however real-time execution requires timely specialist advice and guidance to mitigate drilling hazards. Drilling hazards provide tell-tale signs, and if these signs are captured early, corrective actions can be taken to reduce or completely avoid their impact, reducing operational risk and well delivery costs. This paper describes an expert system that has been developed to offer immediate guidance to support the delivery of specific real-time specialist advice – based on the system’s self-learning of previous drilling events. The expert system monitors real-time drilling parameters and uses case-based reasoning (CBR) to recognize and capture current incidents that are similar to those that have occurred in the past. The system can be used to prevent drilling problems before they occur with real-time case-based reasoning for enhanced risk assessment and hazard mitigation. The paper will review examples of packoffs, stuck pipe and lost circulation that have been mitigated.

Publisher

SPE

Cited by 1 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3