Machine Learning and Data Science in the Oil and Gas Industry: Best Practices, Tools, and Case Studies

Dedication_2021_Machine-Learning-and-Data-Science-in-the-Oil-and-Gas-Industr
Front-matter_2021_Machine-Learning-and-Data-Science-in-the-Oil-and-Gas-Indus
Copyright_2021_Machine-Learning-and-Data-Science-in-the-Oil-and-Gas-Industry
Contributors_2021_Machine-Learning-and-Data-Science-in-the-Oil-and-Gas-Indus
Foreword_2021_Machine-Learning-and-Data-Science-in-the-Oil-and-Gas-Industry
Chapter-1---Introduc_2021_Machine-Learning-and-Data-Science-in-the-Oil-and-G
Chapter 1 - Introduction
1.1 - Who this book is for
1.2 - Preview of the content
1.3 - Oil and gas industry overview
1.4 - Brief history of oil exploration
1.5 Oil and gas as limited resources
1.6 - Challenges of oil and gas
References
Chapter-2---Data-Science--Statist_2021_Machine-Learning-and-Data-Science-in-
Chapter 2 - Data Science, Statistics, and Time-Series
2.1 - Measurement, uncertainty, and record keeping
2.1.1 - Uncertainty
2.1.2 - Record keeping
2.2 - Correlation and timescales
2.3 - The idea of a model
2.4 - First principles models
2.5 - The straight line
2.6 - Representation and significance
2.7 - Outlier detection
2.8 - Residuals and statistical distributions
2.9 - Feature engineering
2.10 - Principal component analysis
2.11 - Practical advice
References
Chapter-3---Machine-Lea_2021_Machine-Learning-and-Data-Science-in-the-Oil-an
Chapter 3 - Machine Learning
3.1 - Basic ideas of machine learning
3.2 - Bias-variance complexity trade-off
3.3 - Model types
3.3.1 - Deep neural network
3.3.2 - Recurrent neural network or long short-term memory network
3.3.3 - Support vector machines
3.3.4 - Random forest or decision trees
3.3.5 - Self-organizing maps (SOM)
3.3.6 - Bayesian network and ontology
3.4 - Training and assessing a model
3.5 - How good is my model?
3.6 - Role of domain knowledge
3.7 - Optimization using a model
3.8 - Practical advice
References
Chapter-4---Introduction-to-Machine-Le_2021_Machine-Learning-and-Data-Scienc
Chapter 4 - Introduction to Machine Learning in the Oil and Gas Industry
4.1 - Forecasting
4.2 - Predictive maintenance
4.3 - Production
4.4 - Modeling physical relationships
4.5 - Optimization and advanced process control
4.6 - Other applications
References
Chapter-5---Data-Management-from-t_2021_Machine-Learning-and-Data-Science-in
Chapter 5 - Data Management from the DCS to the Historian
5.1 - Introduction
5.1.1 - Convergence of OT and IT
5.1.2 - A maturity model for OT/IT convergence
5.1.3 - Digital Oilfield 2.0 headed to the edge
5.2 - Sensor data
5.2.1 - There are problems with data from sensors: data quality challenges
5.2.2 - Validation, estimation, and editing (VEE)
5.3 - Time series data
5.4 - How sensor data is transmitted by field networks
5.4.1 - From Plant to Field: Communications Protocols (HART, Fieldbus, OPC, OPC-UA and Wireless Hart)
5.4.2 - Wireless SCADA radio
5.4.3 - Which protocol is best?
5.5 - How control systems manage data
5.5.1 - Cloud-based SCADA and web-based SCADA
5.6 - Historians and information servers as a data source
5.6.1 - What can you record in a data historian?
5.7 - Data visualization of time series data—HMI (human machine interface)
5.7.1 - Asset performance management systems (APM)
5.7.1.1 - Process control and alarm management
5.7.2 - Key elements of data management for asset performance management
5.7.2.1 - What is an asset registry?
5.7.2.2 - What is the definition of data taxonomy?
5.7.2.3 - What is the definition of data ontology?
5.8 - Data management for equipment and facilities
5.8.1 - What is a document management system?
5.9 - Simulators, process modeling, and operating training systems
5.10 - How to get data out of the field/plant and to your analytics platform
5.10.1 - Data visualization
5.10.1.1 - From historians to a data infrastructure
5.10.2 - Data analytics
5.10.3 - Three historical stages of industrial analytics
5.10.3.1 - Where is data analytics headed?
5.11 - Conclusion: do you know if your data is correct?
References
Chapter-6---Getting-the-Most-Acr_2021_Machine-Learning-and-Data-Science-in-t
Chapter 6 - Getting the Most Across the Value Chain
6.1 - Thinking outside the box
6.2 - Costing a project
6.3 - Valuing a project
6.3.1 - How to measure the benefit
6.3.2 - Measuring the benefit
6.4 - The business case
6.5 - Growing markets, optimizing networks
6.6 - Integrated strategy and alignment
6.7 - Case studies: capturing market opportunities
6.8 - Digital platform: partner, acquire, or build?
6.9 - What success looks like
Chapter-7---Project-Management-for-_2021_Machine-Learning-and-Data-Science-i
Chapter 7 - Project Management for a Machine Learning Project
7.1 - Classical project management in oil & gas-a (short) primer
7.2 - Agile-the mindset
7.3 - Scrum-the framework
7.3.1 - Roles of scrum
7.3.2 - Events
7.3.3 - Artifacts
7.3.4 - Values
7.3.5 - How it works
7.4 - Project execution-from pilot to product
7.4.1 - Pilot setup
7.4.2 - Product owner
7.4.3 - Development team
7.4.4 - Scrum master
7.4.5 - Stakeholders
7.5 - Management of change and culture
7.6 - Scaling-from pilot to product
7.6.1 - Take advantage of a platform
7.6.2 - Establish a team and involve the assets
7.6.3 - Keep developing
7.6.4 - Involve UX expertise
References
Further reading
Chapter-8---The-Business-of-_2021_Machine-Learning-and-Data-Science-in-the-O
Chapter 8 - The Business of AI Adoption
8.1 - Defining artificial intelligence
8.2 - AI impacts on oil and gas
8.2.1 - Upstream impacts
8.2.2 - Downstream impacts
8.2.3 - Production and midstream impacts
8.2.4 - New business models
8.3 - The adoption challenge
8.3.1 - The uncertainties of new technology
8.3.2 - AI in the field
One: Correct predictable analysis
Two: Correct unpredictable analysis
Three: Incorrect predictable analysis
Four: Incorrect unpredictable analysis
8.4 - The problem of trustf
8.4.1 - Work is evolving
8.4.2 - Driverless transportation
8.4.3 - Trust and the machine
8.4.4 - The human-smart machine trust gap
8.4.5 - Trusting a smart machine
8.4.6 - Trusting the smart machine developer
8.4.7 - Making it real
8.4.8 - Getting to trust
8.5 - Digital leaders lead
8.5.1 - Finding the digital leader
8.5.2 - Moving beyond trials and pilots
8.5.3 - The role of trials and pilots
8.5.4 - The economics of pilot projects
8.5.5 - Moving to enterprise deployment
Customer tactics
Technology supplier tactics
8.6 - Overcoming barriers to scaling up
8.6.1 - The scale mismatch
8.6.2 - Supplier consolidation
8.6.3 - The corporate accelerator
8.6.4 - The oil company investor
8.7 - Confronting front line change
Greed
Fear
Pride
8.7.1 - The corporate parallels
8.7.2 - Early warning signs
The digital narrative
Manage the pace
Execution challenges
8.8 - Doing digital change
8.8.1 - A typical change champion
8.8.2 - Organizational reaction to change
Honor the past, define the future
CEO as change leader
Communicate
Be purpose driven
Think big, start small, be agile
Build cyber security in
Stay the course
Chapter-9---Global-Practice-of-AI-and-_2021_Machine-Learning-and-Data-Scienc
Chapter 9 - Global Practice of AI and Big Data in Oil and Gas Industry
9.1 - Introduction
9.2 - Integrate digital rock physics with AI to optimize oil recovery
9.2.1 - The upstream business
9.2.2 - Digital core technology
9.2.3 - Modeling wettability at the pore-scale
9.3 - The molecular level advance planning system for refining
9.3.1 - Prediction of crude oil mixing and molecular properties
9.3.2 - Scheduling optimization at the molecular level
9.3.3 - Collaborative optimization of the entire industry chain
9.4 - The application of big data in the oil refining process
9.4.1 - Principle and methodology
9.4.2 - A case study of CCR process unit
9.5 - Equipment management based on AI
9.5.1 - Equipment hazard monitoring and warning
9.5.2 - Equipment fault recognition and diagnosis
9.5.3 - Equipment health status, residual life prediction and other management
References
Chapter-10---Soft-Sensors-for_2021_Machine-Learning-and-Data-Science-in-the-
Chapter 10 - Soft Sensors for NOx Emissions
10.1 - Introduction to soft sensing
10.2 - NOx and SOx emissions
10.3 - Combined heat and power (CHP)
10.4 - Soft sensing and machine learning
10.5 - Setting up a soft sensor
10.6 - Assessing the model
10.7 - Conclusion
References
Chapter-11---Detecting-Electric-Su_2021_Machine-Learning-and-Data-Science-in
Chapter 11 - Detecting Electric Submersible Pump Failures
11.1 - Introduction
11.2 - ESP data analytics
11.3 - Principal Component Analysis
11.4 - PCA diagnostic model
11.5 - Case study: diagnosis of the ESP broken shaft
11.5.1 - Selection of the ESP broken shaft variables
11.5.2 - Score of principle components
11.5.3 - Pump broken shaft identification
11.6 - Conclusions
References
Further reading
Chapter-12---Predictive-and-Diagnost_2021_Machine-Learning-and-Data-Science-
Chapter 12 - Predictive and Diagnostic Maintenance for Rod Pumps
12.1 - Introduction
12.1.1 - Beam pumps
12.1.2 - Beam pump problems
12.1.3 - Problem statement
12.2 - Feature engineering
12.2.1 - Library-based methods
12.2.2 - Model-based methods
12.2.3 - Segment-based methods
12.2.4 - Other methods
12.2.5 - Selection of features
12.3 - Project method to validate our model
12.3.1 - Data collection
12.3.2 - Generation of training data
12.3.3 - Feature engineering
12.3.4 - Machine learning
12.3.5 - Summary of methodology
12.4 - Results
12.4.1 - Summary and review
12.4.2 - Conclusion
References
Chapter-13---Forecasting-Sluggin_2021_Machine-Learning-and-Data-Science-in-t
Chapter 13 - Forecasting Slugging in Gas Lift Wells
13.1 - Introduction
13.2 - Methodology
13.3 - Focus projects
13.3.1 - Dashboarding landscape/architecture
13.3.2 - Slugging
13.4 - Data structure
13.5 - Outlook
13.6 - Conclusion
Further reading
Index_2021_Machine-Learning-and-Data-Science-in-the-Oil-and-Gas-Industry