Statistical Method for Error Prediction in Decision Support and Control Systems

Aghito, Manuel

doi:10.2118/184735-ms

SPE/IADC Drilling Conference and Exhibition 2017

DOI: 10.2118/184735-ms

|View full text |Cite

Statistical Method for Error Prediction in Decision Support and Control Systems

Manuel Aghito

Abstract: A statistical method for improving the accuracy of predictive mathematical models used in drilling operations is proposed. The scheme can be applied in drilling automation, for example for improving accuracy in automated control systems such as managed pressure drilling (MPD), and for more reliable real-time monitoring and decision support systems. The proposed method is applied to a simulated case of MPD. Hydraulic model predictions of BHP are continuously compared to PWD readings. A short sequ… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2020

Publication Types

Select...

Other2

Relationship

Self Cite0

Independent2

Authors

Journals

Cited by 2 publications

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Hybrid Approach for Drilling Automation

Aghito

Bjorkevoll

2020

Day 2 Tue, November 03, 2020

View full text Add to dashboard Cite

Objectives/Scope The objective of this work is to present a first step towards a hybrid approach between machine learning (ML) and physics-based modelling to provide decision support for drilling problems. The motivation for developing a hybrid approach is to obtain methods that are more reliable and easier to automate than physics-based models, while still have enough accuracy and predictivity. In this first step, we replicate the performance for predicting downhole pressure in a well of a high-fidelity simulator based upon physical principles by using ML methods. In addition, we also suggest a future roadmap. Methods, Procedures, Process A high-fidelity physics-based model for drilling and well control operations is used to generate vast amounts of data for two cases, drilling with not major events, and drilling into an over-pressured reservoir. Key simulation input parameters and assumptions are varied to create realistic scenarios. We replicate the high-fidelity simulator downhole pressure predictions by two supervised machine learning algorithms. Random forest (RF) and recurrent neural network (RNN). The hybrid approach is flexible and is also employed for kick detection and estimation of the mass of the influx. After using unaltered data from the high-fidelity simulator, we also demonstrate the ML methods on corrupted data with synthetic noise. Results, Observations, Conclusions RF and RNN obtained very high accuracy, predicting bottom hole pressure with small error margin. Good results were also obtained for the kick estimation and kick detection cases. Tested on corrupted data, RF trained with noise performed significantly better compared to RF trained without noise, at the cost of a slight reduction in accuracy in the error free scenario. Initials tests on real data are ongoing and further work is needed. Hybrid methods have the potential of performing well with noisy environments and are valuable tool to be used in drilling automation. Novel/Additive Information Combining highly advanced dynamic models for drilling and well control with modern ML methods has not been done earlier to the best knowledge of the authors. Demonstrating this on real data will be valuable because data-driven and physics-based approaches used separately are considered inadequate for future automated drilling concepts.

show abstract

Hybrid Approach for Drilling Automation

Aghito

Bjorkevoll

2020

Day 2 Tue, November 03, 2020

View full text Add to dashboard Cite

show abstract

Autoviscosity - A Vital Step Towards Automation of the Drilling Fluid Process on Drilling Rigs

Bjorkevoll

Aghito

Lund

et al. 2020

Day 1 Mon, November 02, 2020

View full text Add to dashboard Cite

Objectives/Scope The paper describes what steps have been taken towards improved monitoring and control of the offshore drilling fluid process. These steps include the following: Methods, Procedures, Process The predictive viscosity model tracks the active fluids, calculates additives concentrations in the flow loop, analyses sensor data, calibrates viscosity response to additives, and estimates what is needed to obtain the set target rheology. Laboratory and full-scale tests both onshore and offshore have been performed using the automated rheology and density sensor. To prepare for automating the drilling fluid conditioning process, the predictive rheology model was integrated with the drilling fluid control system and sensor data. Additionally, integration with database and cloud service was implemented to facilitate transfer of data from the rig to the onshore. Results, Observations, Conclusions During laboratory scale experiments, the predictive rheology model represented topology flexibly and was configured to represent the active flow loops in laboratory scale experiments, full scale onshore test, and offshore test with two sensors in the loop. The data processing algorithm with data quality assessment and model calibration was tested with onshore full-scale data. Many challenges were addressed and solved by cooperating partners in the integrated fluid laboratory, which included two sensors, the predictive rheology model, drilling fluid control system and a flow loop with multiple active tanks and mixing lines with dosing units for adding liquids and powders. The first response tests for the calculated additive rate set-point were successfully performed. Full-scale onshore tests were completed while adding different additives and recording the rheology data. The calibrated predictive model showed good correlation with the recorded data. Temperature effects were also considered and modelled accurately. Two sensors were installed offshore, recording data during regular drilling operations. Novel/Additive Information New elements required to automate the drilling fluid treatment process have been implemented and tested, including a predictive rheology model and data integration between different vendor's software/control systems and equipment.

show abstract

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.

Contact Info

customersupport@researchsolutions.com

10624 S. Eastern Ave., Ste. A-614

Henderson, NV 89052, USA

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

Blog Terms and Conditions API Terms Privacy Policy Contact Cookie Preferences Do Not Sell or Share My Personal Information

Made with 💙 for researchers

Part of the Research Solutions Family.

Statistical Method for Error Prediction in Decision Support and Control Systems

Cited by 2 publications

References 8 publications

Hybrid Approach for Drilling Automation

Hybrid Approach for Drilling Automation

Autoviscosity - A Vital Step Towards Automation of the Drilling Fluid Process on Drilling Rigs

Contact Info

Product

Resources

About