Real-Time Diagnostics of Gas Lift Systems: A Case Study

Abstract

This article, written by Senior Technology Editor Dennis Denney, contains highlights of paper SPE 124926, ’Real-Time Diagnostics of Gas Lift Systems Using Intelligent Agents: A Case Study,’ by G. Stephenson, SPE, Occidental Petroleum; R. Molotkov, SPE, Weatherford; and N. De Guzman, SPE, and L. Lafferty, SPE, Intelligent Agents Corporation, prepared for the 2009 SPE Annual Technical Conference and Exhibition, New Orleans, 4-7 October; revised for publication. The paper has been peer reviewed. Published: February 2010 SPE Production & Operations, page 111. One problem related to the operation of gas lift wells is the ability to identify underperforming wells and to address the underlying issues appropriately and in a timely manner. This problem is compounded by a trend toward leaner operations and relative scarcity of application-specific domain knowledge. A method is presented that leverages real-time data, gas lift domain expertise, and proven steady-state analysis techniques in a desktop software application. Introduction For cases in which these resources are limited or unavailable, automation technology could be a solution. To assist production engineers in the well-by-well optimization of gas lift systems, a system was developed that uses intelligent software agents that leverage both real-time data and gas lift domain knowledge to assist engineers in these well-by-well optimization tasks. Challenges With Historical Approach One of the most fundamental challenges is that the historical approach tends to be both reactive and episodic in nature, resulting in missed opportunities for production enhancement. Much of this work requires individuals with specialized artificial-lift-domain expertise, which is increasingly scarce as the demographics of the industry change. The ability to detect and address the numerous opportunities in a field is limited by the labor-intensive nature of the work and the volume of competing priorities. It is common for problems in gas lifted wells to go undetected for months or even years because gas lift is such a forgiving artificial-lift method. Even those gas lifted wells that have a serious performance problem and are not producing optimally will often continue to produce fluids. With other forms of lift, failures tend to be catastrophic in nature and are identified and addressed much more quickly. Addressing the Need A system was developed to provide real-time diagnostics of continuous gas lift wells. The system enables decisions that optimize wells. The system provides engineers with the status of all gas lifted wells under their control. Software agents monitor the wells’ situation by collecting and filtering data, assessing the meaning of those data, recommending actions for correcting problems and responding to threats, and explaining their assessment results and recommendations. Agents can detect the initial symptoms of a problem and prompt for corrective action before well performance degrades seriously. The performance of these key functions enables surveillance engineers to optimize many more wells on a continuous basis. The agents integrate continuous data, such as pressure readings, with well-test data and predictions from commercially available systems-analysis tools, and use diagnostic principles stored in a knowledge base to determine each well’s condition and recommend corrective action. The agent reviews all gas lifted wells in the field and prioritizes recommended actions in accordance with pre-established criteria that include increased production potential and possible cost efficiencies.