A Step by Step Approach to Improving Data Quality in Drilling Operations: Field Trials in North America

Abstract

Multiple literature studies have indicated that a significant amount of data collected during drilling operations is unreliable. To move towards better data quality, two critical hurdles need to be overcome. First, the case for the value of good data needs to be made, so that resources can be allocated towards improving data quality. Second, a process needs to be established within the operator company to measure and improve the quality of data. This paper is a case study in addressing these challenges. In this work, we focus on eight core surface sensor measurements essential to drilling operations (block position, hook load, rotary speed, rotary torque, pump strokes per minute, flow rate out, standpipe pressure and pit volume) and attempt to assess/improve their quality. The first step involves identifying how much of each measured data deviates from their accepted values. This is most economically accomplished using automated data validation software. Once the root cause is identified, steps can be taken to rectify the problem. Four rigs in North America were identified for this trial conducted over a six-month period. The goal is to establish a data quality improvement loop that continually accesses data, identifies issues, and implements corrective actions. This paper explains this process and how it has been applied to improve the quality of drilling data.

A Game-Theoretic Approach to Improve Energy-Related Data

“…But due to the operations’ tough environment, a substantial amount of these data sets was not accurate. 7 , 8 As a result, developed AI models could not be fully upscaled the real-time operations; 9 the bottleneck was the data quality. The low-quality data points negatively affected the AI models’ performance, resulting in bad analysis and poor recommendations.…”

“… 12 The administrative approaches propose using key performance indicators (KPIs) to evaluate the quality of data 12 and to develop a data quality dashboard, 13 real-time data quality center, 12 , 14 and others. The method approaches apply a manual cleansing process, 7 remove bias, 15 remove outliers, 16 correlate the data together, 17 smooth the data set, 7 and others.…”

“…As a result, multiple drilling-related AI models were developed such as stuck pipe detection, BHA monitoring, tool wear and flank wear analysis, , rate of penetration (ROP) prediction, formation top prediction, and much more. But due to the operations’ tough environment, a substantial amount of these data sets was not accurate. , As a result, developed AI models could not be fully upscaled the real-time operations; the bottleneck was the data quality. The low-quality data points negatively affected the AI models’ performance, resulting in bad analysis and poor recommendations.…”

Web Enabled High Fidelity Drilling Computer Model with User-Friendly Interface for Education, Research and Innovation

“…During a drilling operation large amount of data is collected. However, the amount of information that can be retrieved from the data is often sparse, and the efforts to use the data for analysis and process control purposes is very challenging (Arnaout et al 2013; Ashok, et al 2016;Maidla et al 2018;Cayeux et al, 2013a). The lack of high-quality data and information about the data (metadata) also hinders technology development and demonstration of innovative solutions in realistic environments.…”

“…However, technology can be tested and demonstrated in a simulated environment up to a certain technology readiness level. IRIS, together with Statoil and Sekal 2 has experience with the DrillTronics TM system where advanced drilling control software has been tested extensively through many years in a simulated environment (Cayeux et al 2012). Worldwide, there are several drilling simulators available that include both transient hydraulics-and drill string mechanic computations.…”