Ensemble methods for process monitoring in oil and gas industry operations

Sui, Dan; Nybø, Roar; Gola, Giulio; Roverso, Davide; Hoffmann, Mario

doi:10.1016/j.jngse.2011.05.004

Cited by 20 publications

(6 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In theory, this correlation could be utilized to get a more accurate picture of the drilling operation. But while we have seen this benefit materialize prediction problems [24], it does not appear to be the case for classification by fuzzy c-means clustering, at least not for the problems studied in this paper. We find that clustering with a careful selection of variables beats using all available data.…”

Section: Part II -Anomaly Detection By Clusteringmentioning

confidence: 67%

Closing the Integration Gap for the Next Generation of Drilling Decision Support Systems

Nybø

Sui

2014

All Days

Self Cite

View full text Add to dashboard Cite

This paper identify the lack of integration between drilling decision support systems and their users as a barrier towards better decision support and increased drilling automation. In part one of this paper we outline the workings of a next generation of decision support systems that reduce this gap. In part two we present our preliminary results with a time series anomaly detection technique, which the decision support systems we have described would require. Part I -IntroductionThroughout the development of integrated operations and intelligent energy, there is a shared expectation of better decision support in the future. This is to be achieved both through better collaboration between people and through improved data analysis and modelling. For the latter, the most frequently cited challenges are data quality [1, 2] and breaking down "data silos" to make data easier to find and integrate with other data sources, or to make different computer systems talk to each other. Another expectation is increased levels of automation, where the aforementioned decision support is gradually expanded to let the computer not only advice on a decision, but to actually make the decision and carry it out. This too requires a close integration of sensors, different computer systems and machinery.

show abstract

Section: Part II -Anomaly Detection By Clusteringmentioning

confidence: 67%

Closing the Integration Gap for the Next Generation of Drilling Decision Support Systems

Nybø

Sui

2014

All Days

Self Cite

View full text Add to dashboard Cite

show abstract

“…Recent work involves passing not only the new target values but also the economics from the RTO applications to the MPC applications as well [43,10]. Ensemble methods increase the reliability of the control methods, much like redundant sensors or physical equipment increase the reliability of operations by making the system less sensitive to a single failure [54]. Fig.…”

Section: Frequency Of Optimization Updatesmentioning

confidence: 99%

Overview of estimation methods for industrial dynamic systems

Hedengren

Eaton

2015

Optim Eng

View full text Add to dashboard Cite

Measurement technology is advancing in the oil and gas industry. Factors such as wireless transmitters, reduced cost of measurement technology, and increased regulations that require active monitoring tend to increase the number of available measurements. There is a clear opportunity to distill the recent flood of measurements into relevant and actionable information. Common methods to do this include a filtered bias update, Implicit Dynamic Feedback, Kalman Filtering, and Moving Horizon Estimation. The purpose of these techniques is to validate measurements and align imperfect mathematical models to the actual process. Additionally, they can determine a best-estimate of the current state of the process and any potential disturbances. These methods allow potential improvements in earlier detection of disturbances, process equipment faults, and improved state estimates for optimization and control.

show abstract

“…Many works focus on the prediction and optimization of the rate of penetration (ROP) using machine learning methods, see e.g., (Sui et al, 2013), (Wallace et al, 2015), (Hegde et al, 2015), (Hegde and Gray, 2017). Others consider the task of predicting the bottom hole pressure, see e.g., (Sui et al, 2011), (Gola et al, 2012), (Sui et al, 2012). In (Roberts et al, 2016) the task of detecting and recognizing a kick is studied from a cognitive point of view; a decision tree is designed to aid the driller in the detection and reaction to the kick.…”

Section: Introductionmentioning

confidence: 99%