Drilling technology for oil and gas exploration has evolved continuously based on feedback from operational experience. With the operators' focus on drilling more challenging unconventional wells, the biggest drivers are efficiency and operating cost. Operators want more real-time information during drilling to provide early warning of potential problems and take corrective actions. Service providers are meeting these challenges with technology improvements that are more robust and automated. The main focus for service providers is improving reliability throughout the service life of the tool while reducing maintenance cost. Consequently, in the past few years there is growing interest in the oil and gas industry towards developing technology and tools to gather more real-time downhole data and use analytical algorithms for fault diagnostics and health prognostics of components in drilling systems. This paper develops the framework and algorithms for constructing data-driven component life models and utilizing them to optimize operational efficiency and extend the life of the drilling system. The key driver behind this approach it to minimize the overall life cycle cost of tools which includes the cost of maintenance and cost of failure. The optimization variables are maintenance intervals and operational parameters (e.g. rpm, weight on bit, etc.) that should be tuned to achieve a desired level of drilling efficiency and reliability. Mathematical models for predicting the life of critical components in the drilling system is developed a-priori by using design qualification test data, operational data, drilling dynamics and historical FRACAS (Failure reporting analysis and corrective action system) information. The framework developed in this paper utilizes these predictive life models for making operations and maintenance decisions at various stages during the life cycle of the tools. The methodology developed in this paper is used to optimize the operational parameters and maintenance intervals for two designs of the bottomhole assembly namely (a) rotary steerable system without motor and (b) rotary steerable system with motor. Tradeoff of maintenance cost and operational performance is studied for different level of operational parameters. The results presented in this paper show that significant improvements in operational efficiency and maintenance intervals can be optimized by using downhole operations and predictive analytics.

You can access this article if you purchase or spend a download.