22
Data Analytics and Asset Management Application of Data Collected Through the IoT Mark Reynolds Senior Solutions Architect, Upstream Integrated Operations final – 09/15/2015

2015 09-16 io t in oil and gas

Embed Size (px)

Citation preview

Page 1: 2015 09-16 io t in oil and gas

Data Analytics andAsset Management

Application of Data Collected Through the IoT

Mark ReynoldsSenior Solutions Architect,

Upstream Integrated Operations

final – 09/15/2015

Page 2: 2015 09-16 io t in oil and gas

2

Introduction to Southwestern Energy

Southwestern Energy Company is a growing independent energy company primarily engaged in natural gas and crude oil exploration, development and production within North America. We are also focused on creating and capturing additional value through our natural gas gathering and marketing businesses, which we refer to as Midstream Services.

Source: http://www.swn.com/

Page 3: 2015 09-16 io t in oil and gas

3

This presentation addresses the ramifications of IoT to the

application of Systems Engineering process for O&G Development teams. Particular attention will be given to the

methodology of IoT application and the challenges of the

Learning Organization.

Application of Data Collected Through the IoT

AbstractThe IoT is a game-changer opening the Systems Engineer and

the Data Scientist to the O&G Development teams. Upstream,

mid-stream, and downstream segments of the market are

confronted by the big question “Now what?”

Page 4: 2015 09-16 io t in oil and gas

4

What is IT? What is OT?

Information Technology (IT)

Traditional - Manage Corporate Accounting Data &

Information

Transitional - Analytics (forensic, observable, predictive)

New / Evolving - Real-time (system control, observable

prediction)Operational Technology (OT)

Traditional - Machine Control

- Process and Flow Control

- Remote Monitoring

Source: Mark Reynolds, compilation

O&GSystemsEngineer

Page 5: 2015 09-16 io t in oil and gas

5

What is all of the Jibber-Jabber about IoT?

Simply put this is the concept of basically connecting any device with an on and off switch to the Internet (and/or to each other). This includes everything from cell phones, coffee makers, washing machines, headphones, lamps, wearable devices and almost anything else you can think of. This also applies to components of machines, for example a jet engine of an airplane or the drill of an oil rig.

Source: Mark Reynolds, compilationA Simple Explanation Of 'The Internet Of Things‘ https://www.linkedin.com/pulse/simple-explanation-internet-things-mohammad-parsa-rozbahani

Information TechnologyInternet of ThingsoTITOTI

Operations Technology

Page 6: 2015 09-16 io t in oil and gas

6

IOT

What is all of the Jibber-Jabber about IoT?

Internet of ThingsIoT InterconnectedOperations TechnologyConnecting

SensorsTerminals

Collecting

InterfacesStandards

Accessing

PresentationsOps Centers

Analyzing

TrendsComparisonsPredictions

Integrating

SystemsCollaborationsAutomations

Source: Mark Reynolds, compilation

Page 7: 2015 09-16 io t in oil and gas

7

When will IOT Become a Game Changer?

2.5% 13.5% 34% 34% 16%http://www.gartner.com/technology/research/methodologies/hype-cycle.jsp 2015

Page 8: 2015 09-16 io t in oil and gas

8

Where is IoT on the Gartner Hype Cycle?

Source: Gartner's 2014 Hype Cycle for Emerging Technologies Maps the Journey to Digital Business, August 11, 2014http://www.gartner.com/newsroom/id/2819918

Page 9: 2015 09-16 io t in oil and gas

9

How will Systems Engineering & Data Science Contribute?

Source: http://www.oralytics.com/2012/06/data-science-ishttp://www.hanyang.ac.kr/code_html/Y3YABD/introEng/img/2.jpghttp://www.baynote.com/2013/06/whats-the-difference-between-a-data-scientist-an-engineer-and-an-analyst-actually-quite-a-lot/

Systems Engineeringis Multidisciplinary

Page 10: 2015 09-16 io t in oil and gas

10

How will Systems Engineering & Data Science Contribute?

Source: http://www.oralytics.com/2012/06/data-science-ishttp://www.hanyang.ac.kr/code_html/Y3YABD/introEng/img/2.jpghttp://www.baynote.com/2013/06/whats-the-difference-between-a-data-scientist-an-engineer-and-an-analyst-actually-quite-a-lot/

Multidisciplinary, but Different Disciplines

Page 11: 2015 09-16 io t in oil and gas

11

How will Systems Engineering & Data Science Contribute?

Source: http://www.oralytics.com/2012/06/data-science-ishttp://www.hanyang.ac.kr/code_html/Y3YABD/introEng/img/2.jpghttp://www.baynote.com/2013/06/whats-the-difference-between-a-data-scientist-an-engineer-and-an-analyst-actually-quite-a-lot/

System Engineer / Data Engineer / Data Scientist?• Experienced, interdisciplinary engineer with a decent understanding of O&G

• Rock star software engineer with a decent understanding of statistics

• Provide the platform upon which the data can be modeled

• Core value lies in ability to [design &] prepare the data pipeline

• Understanding of … distributed computing and database

• Decent understanding of algorithms – O&G, Electronics, Software, Systems

O&G Systems – Data Engineer

Page 12: 2015 09-16 io t in oil and gas

12

How does the O&G Systems – Data Engineer contribute?

O&GSystems–Data

Engineer

O&G Systems

Control Systems

Remote Systems

Information Systems

Embedded Systems

Robotic Systems

Data Fusion

Real-Time Systems

Look-Back Analysis

Look-Ahead Systems

Land and Regulatory

Geology Geophysics

Drilling Engineering

Completion Engineering

Production Engineering

Reservoir Engineering

Systems-Data Engineering

Source: Mark Reynolds, compilation

Page 13: 2015 09-16 io t in oil and gas

13

How do we Approach IoT in the 4th Paradigm?Da

taQu

ality

Data

Integrity

Data

Collections

DataModeling DataSecurity

Data Mining

Data

Analytics

• O&G is where we found itParadigm 1:Empirical

• O&G is where we expect itParadigm 2:Theoretical

• O&G is where we estimate itParadigm 3:Computational

• O&G is where we infer itParadigm 4:Data Exploration

Source: Mark Reynolds, compilation

Page 14: 2015 09-16 io t in oil and gas

14

How do we Approach IoT in the 4th Paradigm?Da

taQu

ality

Data

Integrity

Data

Collections

DataModeling DataSecurity

Data Mining

Data

Analytics

Data

Acquisition & Modelling

Collaboration & Visualization

Analysis & Data Mining

Dissemination & Sharing

Archiving & Preserving

Tradi t ional Data Li fe Cycle

Source: Mark Reynolds, compilation

Page 15: 2015 09-16 io t in oil and gas

15

How do we Approach IoT in the 4th Paradigm?Da

taQu

ality

Data

Integrity

Data

Collections

DataModeling DataSecurity

Data Mining

Data

Analytics

Data Sources

•Spatial•Temporal•Asynchronous•Real-Time

Field Processing

•Signal Processing•Exception Alerts•Autonomous•Streaming

24/7 Centers

•Data Centralization•Field Operations•Proactive•Forensic•Closed-Loop

Plan-ning

•Analytics•Improvements•Systems

4 t h Paradigm Data Li fe Cycle in E&P

Source: Mark Reynolds, compilation

Page 16: 2015 09-16 io t in oil and gas

16

How do we Approach IoT in the 4th Paradigm?Da

taQu

ality

Data

Integrity

Data

Collections

DataModeling DataSecurity

Data Mining

Data

Analytics

Source: Mark Reynolds, compilation

Logging• Static• Forensic• Autonomous• Assigned

Monitoring• Streaming• Real-Time• Configurable• Encompassing

IoT• Streaming• Interconnected• Managed• Pervasive

Internet of Things /Interconnected Operat ions Technology

Page 17: 2015 09-16 io t in oil and gas

17

What are the Challenges for Industrial IoT?

ComputationReal-Time

High Performance

Scalability

Communication

Time Synchronization

Determinism

Interoperability

ControlAdaptive Control

Design Methodology

Models of Computation

Computation

Heterogeneous Processing

Advanced Sensing

Modularity

CommunicationBandwidth & Latency

Synchronization

Security

Design Approach

Complexity

Abstraction

Simulation

Source: National Instrumentshttp://www.slideshare.net/abuayd/talk-on-industrial-internet-of-things-intelligent-systems-tech-forum-2014-public

The Industrial IOT System

The Challenges

Page 18: 2015 09-16 io t in oil and gas

18

What are Challenges in Learning Organizations?

The Learning Organization

Personal Mastery

Mental Models

Building Shared Vision

Team Learning

Systems Thinking

Source: 1990, Peter M SengeThe Fifth Discipline, Doubleday/Currency, ISBN 0-385-26094-6

Collaborate

• Team Collaboration• rather than

• Silos and Handoffs

Add Value

• Maximizing ROI• rather than

• ROP

Orchestrate

• Orchestrating the Services• rather than

• Delineating Jobs and Tasks

Responsive

• Planning to respond to change• rather than

• responding to change in plans

Fi f th Disc ip l ine Organizat ions Agi le Organizat ions

Page 19: 2015 09-16 io t in oil and gas

19

What are Challenges in Learning Organizations?

The Learning Organization

Personal Mastery

Mental Models

Building Shared Vision

Team Learning

Systems Thinking

Source: 1990, Peter M SengeThe Fifth Discipline, Doubleday/Currency, ISBN 0-385-26094-6

Collaborate

• Team Collaboration• rather than

• Silos and Handoffs

Add Value

• Maximizing ROI• rather than

• ROP

Orchestrate

• Orchestrating the Services• rather than

• Delineating Jobs and Tasks

Responsive

• Planning to respond to change• rather than

• responding to change in plans

Learning to be Effective,

Not just Efficient

Fi f th Disc ip l ine Organizat ions Agi le Organizat ions

Page 20: 2015 09-16 io t in oil and gas

20

How has Industry Requirements changed?

Previously Acceptable• Proprietary• Manual Rounds• Schedule Based Maintenance• Human Databases• Limited Visibility

Today’s Demands• Open Architecture• Continuous Monitoring• Predictive Maintenance• Intelligent Advisors• Advance Sensor Fusion

Source: National Instrumentshttp://www.slideshare.net/abuayd/talk-on-industrial-internet-of-things-intelligent-systems-tech-forum-2014-public

Page 21: 2015 09-16 io t in oil and gas

21

Questions?

Q: What is the Objective?

Page 22: 2015 09-16 io t in oil and gas

22

Mark Reynolds

Mark Reynolds Vitae• Southwestern Energy• Lone Star College• Intent Driven Designs• Scan Systems• Sikorsky Aircraft• General Dynamics

• Southwestern Energy Email– [email protected]

22