Dream to Learn is shutting down...

We are very sorry to say that Dream to Learn will be shutting down as of December 28th, 2019. If you have content that you wish to keep, you should make a copy of it before that date.


0COMMENTS0RECOMMENDS

Digital Twins - Part 1

109
POSTED IN: Data Analytics & Visualization Blog

Digital Twins & Digital Threads: A Holistic Approach to Asset Management

cross post from  https://www.linkedin.com/pulse/digital-twins-threads-holistic-asset-management-ryan-anderson

 

Executives visiting us at Watson West in San Francisco often ask for our thoughts on emerging technologies with disruptive potential. More frequently, the topic of "Digital Twin" is being discussed.

If you are not familiar with the concept, here are the high points:

 

  •     Digital Twin is a virtual/digital representation of a physical entity or system
  •     It is a “living model” or “computerized companion” that mirrors an evolving physical asset over time
  •     It often uses 3D CAD designs and data from sensors installed on physical objects, that provide real-time IOT data

There’s a nice summary in Gartner’s Top 10 Strategic Technology Trends for 2017:

http://www.gartner.com/smarterwithgartner/gartners-top-10-technology-trends-2017

 

Delivering Value Today

Digital Twins are delivering benefits to many organizations today - by providing monitoring and diagnostics; leveraging predictive analytics for alerts and preventative maintenance; and weaving together heterogeneous data over the long run to give designers and engineers a better understanding of the equipment – both in field, and on the drawing board. An evolving and holistic view of a complex asset.

 

 Digital Twins are being used in aircraft engines, locomotives, and other complex engineering structures. They are generally a good fit for assets with these traits:

 

  •     Complex Engineering & Long Operating Life
  •     Expensive to Build or Operate
  •     Similar assets have divergent states & stories over time
  •     Ability to be instrumented to provide telemetry data
  •     Failures are expensive and/or can harm people

 

The idea of Digital Twin is not new. Over 15 years ago the concept was presented in a University of Michigan Product Lifecycle Management (PLM) center paper. Related topics also include Condition based maintenance (CBM) and mentions of physics-based models, may bring to mind the Finite Element Analysis (FEA) which has been used for decades in civil and aeronautical engineering.

So what changed? Why the upgrade and Spotlight in 2017?

 

As complementary technologies evolve (including IOT, Blockchain, machine learning, analytics, and cognitive) Digital Twins are becoming even more useful and valuable.

 

My own epiphany came when I explored use cases where Digital Twin intersected with Cognitive Computing (dovetailing with unstructured data and human tribal knowledge) and saw how new insights complemented the other data.

 

 

Human Insights & Tribal Knowledge

 

When taking a holistic approach to the management of complex physical assets over the entire life cycle – the data must extend far beyond CAD design drawings and tidy structured sensor data, and also include the multitude of semi structured and unstructured data helps tell the asset’s story. Maintenance reports, training manuals, testing and inspection logs, comments on weather conditions, conference call transcripts, employee expertise and other semi-formal inter-team communications.

 

An experienced doctor rarely makes a diagnosis based solely on the current vital statistics of patient, but usually talks to the patient to understand her history. Similarly, an engineer should have access to all information about an asset that can help with diagnosis and decision support. 

 

What is said about the asset matters.

 

Deep Thoughts

 

For a great example of asset-centric knowledge capture, we look to the energy sector. Woodside Energy is Australia’s largest independent energy company that operates a complex gas platform in the deep waters of the North West Shelf, 70 miles off the coast of Australia. There’s a great video here (full disclosure, I'm an IBMer )

 

Woodside has done a great job data and information gathering and archiving employees’ reports, decision logs, and technical evaluations. With many experienced engineers retiring, Woodside recognized the risk of losing swaths of irreplaceable institutional knowledge (tribal knowledge) and experience about the complexities of the platform.

 

 Woodside used cognitive computing to capture, curate and make available the (context-relevant) tribal knowledge for education and decision support.  Woodside engineers now have a truly holistic view of their complex asset.

 

Data, dials and now - dialog.

 

ROI and Risk Management – with Digital Twin & Digital Threads.

 

Cognitively-Enabled Digital Twins can deliver the following value to the enterprise:

 

    Increased visibility and confidence in assets (design and operation)

    Reduced risk and improved reliability

    Best fit operation and maintenance plans

    Knowledge Capture and sharing

    Active Asset Management and Asset Life Extension

 

The last point is a big one for me – and one of the reasons it’s now high on my “emerging + disruptive” list....

 

For a company with millions or billions of dollars of assets under management, cognitively-enabled Digital Twins can not only reduce risk and improve decision making around maintenance, but can deliver clear ROI by safely extending the operating life of assets.  And in some cases, Digital Twin "retrofits" might be possible for older assets already deployed in operation.

 

The Extra Mile

 

I had the opportunity to interview a respected railway executive and retired project director. He has nearly 50 years of experience with the design, delivery and operation of a large and complex railway systems.

 

He told me a very interesting story of how his organization got exceptional value out of its rolling stock. KPIs almost unbelievable to people outside the company. Although the typical asset life span of rolling stock was 30 years; his organization has safely extended it to 40, and in some cases nearly 50 years. Keep in mind some of these rail cars were built just after I was born, and are still safely in operation today.

 

His railway was able to do this because of a unique combination of company culture; tribal knowledge; great (old school) record keeping; and top-shelf engineering and maintenance teams. In this case, quality data and knowledge of the rolling stock (and refurbishment investment), resulted in asset life extension of more than 60%. 

 

So, if you are Warren Buffet and BNSF leadership, and operating 8000 locomotives worth more than $10b on 32,000 miles of track and signaling, a double-digit percentage life extension probably sounds pretty good to you - and to Berkshire shareholders.

 

In short - Digital Twins enriched with cognitive and other emerging technologies, can deliver ROI and help manage risk.

 

Digital Threads

 

NIST (National Institute of Standards and Technology) asserts “how a product’s design and manufacturing information is authored, exchanged, and processed is critical to competitiveness … information ‘silos’ for various life cycle processes are slowly being connected to form a ‘digital thread’ of information that is envisioned to integrate and drive modern design, manufacturing and product support processes” – the bi-directional flow of information connecting departments (and companies) increases collaboration, operational agility, and enables end-to-end product traceability, quality management, and visibility into real-time performance metrics.

 

With the evolution of IOT backbone technology, blockchain, and cognitive computing, these digital threads can and should include ALL sources of the data chains that are informative to stakeholders, and:

 

    Extend across the supply chain through to the owner/operator

    Continue for the lifetime of the asset

    Include unstructured data, such as tribal/human intelligence, related to asset

 

For example, if we take a $300m long-haul aircraft: the manufacturer, airline operator, federal regulators, suppliers, maintenance teams, and passengers all benefit from a holistic view and better informed stakeholders. Over the aircraft's lifetime (design, build, furnish, operate, and maintain) the aircraft's Digital Twin evolves with the asset, and the Digital Thread (data chain) feedback loop helps stakeholders connect the dots that matter - to make better decisions at each step of the way. Each rivet has a story.

 

ROI on Retrofits?

 

The value proposition for new, complex, and expensive assets is pretty clear. What will be interesting over the next decade is whether/how Digital Twins can deliver results for:

 

  •     assets already in service (e.g. a 10-year-old ferry with a 40-year lifespan)
  •     less complex / less expensive assets (e.g. a new car)
  •     assets with imperfect CAD or telemetry information (e.g. a house)
  •     aging infrastructure (e.g. Eisenhower’s Interstate & Defense Highways - in today's dollars, it was a half-TRILLION dollar project - and it's all coming up on its 70'th birthday soon)

 

 

Conclusion

 

Gartner’s report on trends pulls it all together nicely “Within three to five years, billions of things will be represented by digital twins, a dynamic software model of a physical thing or system. Using physics data on how the components of a thing operate and respond to the environment as well as data provided by sensors in the physical world, a digital twin can be used to analyze and simulate real world conditions, responds to changes, improve operations and add value. Digital twins function as proxies for the combination of skilled individuals (e.g., technicians) and traditional monitoring devices and controls (e.g., pressure gauges).”

 

Digital Twins enable a holistic view of assets – and better information enables better stewardship.

 

 

Sources:

 

1.    https://en.wikipedia.org/wiki/Digital_Twins

 

2.    http://www.gartner.com/smarterwithgartner/gartners-top-10-technology-trends-2017

 

3.    https://www.infosys.com/insights/services-being-digital/Documents/future-industrial-digital.pdf

 

4.    https://www.ibm.com/blogs/internet-of-things/new-digital-twin-capabilities/

 

5.    https://www.ibm.com/blogs/internet-of-things/digital-twin/

 

6.    https://www.ibm.com/internet-of-things/iot-zones/iot-buildings/sensors-in-intelligent-buildings/

 

7.    https://www.youtube.com/watch?v=2dCz3oL2rTw

 

8.    https://community.plm.automation.siemens.com/t5/Digital-Transformations/Four-important-digital-twin-takeaways-for-every-industry/ba-p/357260

 

9.    https://www.forbes.com/sites/bernardmarr/2017/03/06/what-is-digital-twin-technology-and-why-is-it-so-important/

 

10. https://www.researchgate.net/publication/307509727_Origins_of_the_Digital_Twin_Concept

 

11. https://en.wikipedia.org/wiki/Condition-based_maintenance

 

12. https://en.wikipedia.org/wiki/BNSF_Railway

 

13. https://www.ibm.com/watson/stories/woodside.html

 

14. https://www.youtube.com/watch?v=GFZ2IaTVkY8

 

15. https://medium.com/cognitivebusiness/tap-into-your-tribal-knowledge-48a3786df081

 

16. https://www.nist.gov/sites/default/files/documents/el/msid/1Kraft_DigitalThread.pdf

 

17. https://www.nist.gov/programs-projects/digital-thread-smart-manufacturing

 

 

 

 

Interested in more content by this author?

About the Author

Ryan Anderson

Ryan Anderson

Hi! I like to play with data, analytics and hack around with robots and gadgets in my garage. Lately I've been learning about machine learning.

About this blog

Description is...<br/>Data Analytics & Visualization Blog - Generating insights from Data since 2013

Created: July 25, 2014

Englishfrançais

Up Next