Pattern recognition-based remaining useful life estimation of bottomhole assembly tools

Garvey D.R., Baumann J., Lehr J., Hughes Baker, Hines J.W.

Abstract:
This paper describes a new pattern recognition based system for estimating the remaining useful life (RUL) of bottomhole assembly (BHA) tools. Modern drilling equipment operates in increasingly severe environments, with downhole temperatures in excess of 200°C and high impact vibration events being common. Additionally, rig operators are asking tools to perform mission profiles that have previously been impossible, thereby increasing the stress on the downhole tools. All the while, clients are beginning to contractually demand high reliability to help them prevent costly downhole failures and ensure profitability. Current periodic maintenance practices are proving to be insufficient or cost-intensive to meet these new challenges. Because of this, industry is shifting toward simple condition-based maintenance, which uses design guidelines and rough operational thresholds to assess individual tool health. While there is value in the latter approach, there is a large amount of tool performance and environmental data collected during operation that has yet to be effectively incorporated into the health assessment process. This paper addresses this shortcoming by using the available data to infer the RUL of individual tools. Using "real world" data collected from a rotating steering system tool, the prognosis system is shown to be able to predict the RUL of individual tools with an accuracy ranging from 0.88 to 8.76 hours over three test sets. The developed system will allow service providers to make more agile maintenance decisions and provide operators the means to incorporate reliability into the well planning and operations processes, enabling monetary savings for both parties.

回上页