A S M E

S T B - 1 - 2 0 2 0

Gu id e line o n Big Data/Digital Transfo rmation Wo rkflo ws and Applicatio ns for the

Oil and Gas Indu stry

STB-1-2020

GUIDELINE ON BIG DATA/DIGITAL TRANSFORMATION WORKFLOWS AND APPLICATIONS

FOR THE OIL AND GAS INDUSTRY

Prepared by:

Barbara Thompson, P.E. TeamBS, LLC.

Date of Issuance: December 31, 2020

This publication was prepared by ASME Standards Technology, LLC (“ASME ST-LLC”) and sponsored by The American Society of Mechanical Engineers (“ASME”), Petroleum Division.

Neither ASME, ASME ST-LLC, the author, nor others involved in the preparation or review of this document, nor any of their respective employees, members or persons acting on their behalf, makes any warranty, express or implied, or assumes any legal liability or responsibility for the accuracy, completeness or usefulness of any information, apparatus, product or process disclosed, or represents that its use would not infringe upon privately owned rights.

Reference herein to any specific commercial product, process or service by trade name, trademark, manufacturer or otherwise does not necessarily constitute or imply its endorsement, recommendation or favoring by ASME or others involved in the preparation or review of this document, or any agency thereof. The views and opinions of the authors, contributors and reviewers of the document expressed herein do not necessarily reflect those of ASME or others involved in the preparation or review of this document, or any agency thereof.

ASME does not “approve,” “rate”, or “endorse” any item, construction, proprietary device or activity.

ASME does not take any position with respect to the validity of any patent rights asserted in connection with any items mentioned in this document, and does not undertake to insure anyone utilizing a standard against liability for infringement of any applicable letters patent, nor assume any such liability. Users of a code or standard are expressly advised that determination of the validity of any such patent rights, and the risk of infringement of such rights, is entirely their own responsibility.

Participation by federal agency representative(s) or person(s) affiliated with industry is not to be interpreted as government or industry endorsement of this code or standard.

ASME is the registered trademark of The American Society of Mechanical Engineers.

No part of this document may be reproduced in any form, in an electronic retrieval system or otherwise,

without the prior written permission of the publisher.

The American Society of Mechanical Engineers Two Park Avenue, New York, NY 10016-5990 ISBN No. 978-0-7918-7399-1

Copyright © 2020

THE AMERICAN SOCIETY OF MECHANICAL ENGINEERS

All Rights Reserved

TABLE OF CONTENTS

Foreword vii

1. Purpose, Definitions and References 1

   1. Scope 1

      1. How to Use This Guideline 1

   2. Definitions 2

   3. References 10

2. Data Structure and Management 11

   1. Introduction 11

   2. Structured Data 11

      1. Types and Usage 11

      2. Databases 11

      3. Examples 11

   3. Unstructured Data 13

      1. Types and Usage 13

      2. Respective Databases 13

      3. Examples 13

   4. Security and Governance of Data 15

      1. Responsibility of the Enterprise 15

      2. Key Concepts of Information Security 15

      3. Data Protection 15

      4. Developing Software that is Secure 16

      5. Facility Management Systems 16

3. Big Data in the Oil and Gas Industry 17

   1. Introduction 17

      1. Overview 17

      2. Oil and Gas Facility Lifecycle Digital Requirements 17

      3. Designing the Digital Facility 19

      4. Understanding the Data in Oil and Gas Activities 19

   2. Hydrocarbon Reservoirs, Drilling, Production, Transportation and Refining 19

      1. Activities that Produce Data 19

      2. Digital Facility Descriptions 25

   3. Mechanical Equipment and Instrumentation 26

      1. Pressure Control Equipment 26

      2. Rotating Equipment 26

      3. Electrical and Instrumentation 26

      4. Process Control 27

      5. Process Equipment 27

      6. Civil/Structural 28

   4. Pipelines/Storage 28

   5. Operations 28

   6. MetOcean 28

   7. Health and Safety 29

   8. Supply Chain 29

   9. Special Note to this Chapter 30

4. Methods of Analysis 31

   1. General Information on How and When to Use These Methods 31

   2. Descriptive Analytics and Data Mining 33

      1. Importance and Objectives 33

      2. General Statistical Descriptors 34

      3. Descriptive Analytical Tools 34

   3. Predictive Analytics 35

      1. Importance and Objectives 35

      2. Regression Problems and Solutions 36

      3. Classification Problems and Solutions 36

      4. Unstructured Data Problems and Solutions 38

      5. Time Series 39

   4. Prescriptive Analytics 39

      1. Importance and Objectives 39

      2. Optimization Problems and Solutions 39

      3. Simulation Problems and Solutions 39

   5. Application Program Interfaces 39

      1. Importance and Objectives 39

      2. Implementation 40

   6. Visualization Tools 40

5. Data Analytics Project Workflows 41

   1. Introduction 41

      1. CRISP-DM 41

      2. INFORMS and the Job Task Analysis 42

      3. Structure, Roles and Responsibilities 42

      4. Value to the Enterprise 42

   2. Business Problem Framing 43

      1. Description 43

      2. Team Member Roles 44

      3. Example Business Challenge – Permian Basin Production Forecasting 44

   3. Analytics Problem Framing 45

      1. Description 45

      2. Team Member Roles 45

      3. Example Business Challenge - Permian Basin Forecasting Model Continued 46

   4. Data 46

      1. Description 46

      2. Team Member Roles 47

      3. Example Business Challenge - Permian Basin Forecasting Model Continued 48

   5. Methodology Approach and Selection 49

      1. Description 49

      2. Team Member Roles 50

      3. Example Business Challenge - Permian Basin Forecasting Model Continued 50

   6. Model Building and Testing 50

      1. Description 50

      2. Team Member Roles 51

      3. Example Business Challenge - Permian Basin Forecasting Model Continued 51

   7. Solution Deployment 52

      1. Description 52

      2. Team Member Roles 53

      3. Permian Basin Forecasting Model Continued 53

   8. Model Maintenance and Recycle 53

      1. Description 53

      2. Team Member Roles 54

      3. Example Business Challenge - Permian Basin Forecasting Model Concluded 54

   9. The Business Solution 55

      1. The Continuing Challenge 55

      2. The Important Role of the Engineer 55

Mandatory Appendix I: Data Characterization Chart for Oil and Gas 56

I-1 Digital Twin Representation Example 57

Mandatory Appendix II 59

1. Detailed Data Journey 60

2. SIPOC Chart 61

3. Job Function Descriptions 62

4. RACI Chart 63

Nonmandatory Appendix A: Case Study 64

Nonmandatory Appendix B: Certifications Available 78

Nonmandatory Appendix C: Glossary Definitions 80

Copyright Declarations 94

LIST OF TABLES

Table 2-1: Data Description Table 12

Table 4-1: 5S Lean Approach to Data Mining 33

Table 5-1: RACI Chart for Business Framing 44

Table 5-2: Analytics Problem Framing RACI Chart 46

Table 5-3: Data RACI Chart 48

Table 5-4: Methodology Selection RACI Chart 50

Table 5-5: Model Building and Testing RACI Chart 51

Table 5-6: Solution Deployment RACI Chart 53

Table 5-7: Model Lifecycle RACI Chart 54

LIST OF FIGURES

Figure 2-1: Relational Database Example 12

Figure 2-2: Object-Oriented Database Example 12

Figure 2-3: Data Lake Example 14

Figure 2-4: NoSQL Data Types 14

Figure 2-5: Graph Database 14

Figure 3-1: Digital Facility Components 18

Figure 3-2: Onshore and Offshore Seismic Imaging Activities 20

Figure 3-3: Drilling Derrick and Casing Components 21

Figure 3-4: Example Well Log 22

Figure 3-5: Completed Well Example 23

Figure 3-6: Oil and Gas Production Facility 24

Figure 3-7: Gulf of Mexico Pipeline System 24

Figure 3-8: Oil Refining and LNG Processing 25

Figure 3-9: Process Control Graphical User Interface 27

Figure 3-10: Supply Chain Analytics Landscape 30

Figure 4-1: Data Analytics Journey Overview 32

Figure 4-2: Descriptive Analytic Tool Examples 35

Figure 4-3: Decision Tree 37

Figure 4-4: Neural Network 38

Figure 4-5: Data Journey from Source to API 40

Figure 5-1: CRISP-DM Business Process 41

Figure 5-2: Data Selection Decision Tree 47

Figure 5-3: Descriptive Analytics for Permian Basin Data Sets 49

Figure 5-4: Model Comparison Results 52

FOREWORD

Guideline Description

This guideline is the culmination of the efforts of ASME industry professionals in oil and gas to define Big Data and its useful applications to upstream, midstream and downstream businesses.

The concept of Big Data intimidates decision-makers and business leadership. While the introduction of new digital technologies is the cornerstone of the industry’s digital transformation, use of Big Data requires the sharing of asset-specific or operational data of a size and scope that is difficult to grasp. Industry data may also be of poor quality, requiring significant effort and resources to cleanse and aggregate prior to its analysis. In addition, the gathering, aggregation, analysis, and data storage and maintenance is very expensive. The industry needs a standardized and efficient end-to-end workflow to validate the quality of the data, and subsequently, the accuracy of the results from the analysis.

The goal of this document is to alleviate that intimidation by providing a framework for understanding and a workflow for utilizing data analytical techniques to solve business problems; without requiring the reader to be a full-time statistician or data scientist professional.

Who Should Use this Guideline?

The design of this Guideline is intended to be universal in its application to Big Data challenges in the oil and gas industry. It is written not only for oil and gas professionals who are beginners to Big Data techniques but also for data professionals looking to contribute to unique oil and gas applications.

Specific users can be characterized as:

Citizen Data Scientist: a subject matter expert in engineering, operations, supply chain, planning, project management or operations that requires data insights.

Early Career Engineer: a young professional that is looking to improve his or her career by adding a data dimension to their problem solving.

Data Scientist Professional: a data science professional that is looking to apply his or her deep experience in data analytics by learning the unique sets of data and operational challenges of the oil and gas industry.

The author acknowledges, with deep appreciation, the activities of the ASME volunteers and staff who have provided valuable technical input, advice and assistance with review of, commenting on, and editing of, this document, particularly the activities of the Peer Review Group (PRG) consisting of Michael Wells, Thalia Kruger, Amit Kumar, Mete Mutlu, Brian Webster, Kathryn Hyam, and the activities of the ASME Petroleum Division Leaders and Petroleum Division Big Data Task Group consisting of Jim Kaculi, Ed Marotta, John O'Brien, and Jamie Hart.

Established in 1880, ASME is a professional not-for-profit organization with more than 100,000 members and volunteers promoting the art, science and practice of mechanical and multidisciplinary engineering and allied sciences. ASME develops codes and standards that enhance public safety, and provides lifelong learning and technical exchange opportunities benefiting the engineering and technology community. Visit https://www.asme.org/ for more information.

ASME ST-LLC is a not-for-profit Limited Liability Company, with ASME as the sole member, formed in 2004 to carry out work related to new and developing technology. ASME ST-LLC’s mission includes meeting the needs of industry and government by providing new standards-related products and services, which advance the application of emerging and newly commercialized science and technology, and providing the research and technology development needed to establish and maintain the technical relevance of codes and standards. Visit https://asmestllc.org/ for more information.

STB-1-2020: Guideline On Big Data/Digital Transformation Workflows and Applications

1 PURPOSE, DEFINITIONS AND REFERENCES

1.1 Scope

This guideline explains the current use and application of data analytics and data science in the oil and gas industry. It is designed to provide guidance on how to utilize data analytics and machine learning/artificial intelligence (ML/AI) to address a given business need, resulting in value-creation. Within the guidelines will be descriptions of various data analytics techniques and the recommended tools for the respective techniques.

1.1.1 How to Use This Guideline

1. Basics

   This document is designed as both a “how-to” and a reference document. The chapters are arranged in a building block sequence that parallels the journey of a business data project. These building blocks should help provide a roadmap to data-driven projects.

   Each chapter is also a standalone reference for its respective topic. The reader can reference these individual chapters as needed to fill gaps in his or her understanding of either data techniques or oil and gas.

2. Chapters

In this first chapter, the user is introduced to definitions and acronyms common to both oil and gas and to the data analytics strategies highlighted in this guide.

Chapter 2 provides background to the various types of data in the oil and gas industry, including how they are curated, described, used, and safeguarded.

Chapter 3 describes the Digital Facility and the related oil and gas activities and operations that produce data. It also defines the types of data produced by each operation and potential applications for data- driven insights.

Chapter 4 explores the types of data analytics tools available to a data project leader and how they can be utilized. This chapter is where the user can find information about topics such as regression models, classification, machine learning, optimization, and data visualization.

Chapter 5 is a description of a full data project. The user will learn how to structure a project, assemble the appropriate team resources, frame the questions to be answered, model and execute the project, and usefully deploy the resulting model.

Two sets of Appendices are included for references and details that supplement the discussions of the chapters. The Mandatory Appendices are presented to help understand data projects and the team members required to execute them. Nonmandatory Appendices are included to provide the user with additional definitions, sample case studies as examples, and a description of relevant certifications available if the reader wishes to increase his or her knowledge and proficiency in data analytics.