The Geothermal Research Program of the U.S. Department of Energy (DOE) has as one of its goals to reduce the cost of drilling geothermal wells by 25 percent. To attain this goal, DOE continuously evaluates new technologies to determine their potential in contributing to the Program. One such technology is artificial intelligence (AI), a branch o f computer science that, in recent years, has begun to impact the marketplace in a number of fields. Two subsets of AI with potential application to geothermal drilling are expert systems and intelligent machines. Expert systems techniques can (and in some cases, a1 ready have) been appl ied to develop computer-based "advisors" to assi st drilling personnel in areas such as designing mud systems, casing plans, and cement programs, optimizing drill bit selection and bottom hole assembly (BHA) design, and alleviating lost circulation, stuck pipe, fishing, and cement problems. Intelligent machines with sensor and/or robotics directly 1 inked to AI systems, have potential applications in areas o f bit control, rig hydraulics, pipe handling, and pipe inspection. Using a well costing spreadsheet, the potential savings that could be attributed to each of these systems was calculated for three base cases: a dry steam well at The Geysers, a medium-depth Imperial Valley well, and a deep Imperial Valley well. The calculations incorporated costs associated with drilling problems, and assumed that each AI system evaluated would succeed in attaining specific efficiency goals. Based on the average potential savings to be realized, expert systems for handling lost circulation problems and for BHA design are the most likely to produce significant results. Other expert systems, specifically for bit optimization and mud design, would also yield significant savings but will likely be available (or already are) from the oil and gas drilling industry. Effort should concentrate on extending these existing systems to geothermal applications. Automated bit control and rig hydraulics also exhibit high potential savings, but these savings are extremely sensitive to the assumptions of improved drilling efficiency and the cost of these systems at the rig.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.