Differences Between Simulation and Digital Twins

Interesting.  Have done lots of Monte Carlo style simulation modeling, much less using digital twins.   Is this a good description?  For what contexts? .  We also did agent based modeling, which has similarities to DTs.  Anyone with similar experiences have some good thoughts?   Point me to other resource examples of value.    What to collaborate on this?  Say for choice of models or their combination? 

What is the Difference Between a Simulation and a Digital Twin Model?

 15 Apr, 2020  in Exorint

The increasing use of emerging technology to simplify complex tasks has proved rewarding across every industry in diverse ways. This includes increased operational efficiency, automating manual tasks, training and validation, as well as data analysis. It is a known fact that the integration of emerging tech has brought on the fourth industrial revolution, in which data analytics and automation are important components. The digital transformation of traditional processes is also another aspect of Industrie 4.0 and, here, simulation and the digital twin play starring roles. But what are these roles?

This article will discuss:

The definition and application of simulation technology and the digital twin

The differences between a simulation and a digital twin

The symbiotic relationship between simulations and the digital twin

What is simulation?

In computing, simulations refer to digital models that imitate the operations or processes within a system. Such simulations are used for analyzing the performances of systems and the testing and implementation of new ideas. Engineers and technicians make use of simulations across a variety of industries to test products, systems, processes, and concepts.

In many circles, simulations are run using computer-aided design software applications. But for more advanced simulations with many variables, specialized simulation software is used. Typical examples of how simulations function include their use in finite element analysis and stress analysis. In the real world, these tests involve analyzing the effect of external pressure on metals or products to enhance their design or features.

Other types of simulations include discrete event simulations, stochastic simulations, and deterministic simulations. In these types, the variables used in running the simulation are either known or random. To run simulations, some level of digitization is needed. This process may involve only mathematical concepts or the design of 2D or 3D models representing assets within a process or a product. The simulation is then run by introducing variables into the digital environment or interface.

What is a digital twin?

In its basic form, a digital twin is the digital representation of physical or non-physical processes, systems, or objects. The digital twin also integrates all data produced or associated with the process or system it mirrors. Thus, it enables the transfer of data within its digital ecosystem, mirroring the data transfer that occurs in the real world. The data used in digital twins are generally collected from Internet of Things devices, edge hardware, HMIs, sensors, and other embedded devices. Thus, the captured data represents high-level information that integrates the behavioral pattern of digitized assets in the digital twin.

The real-time digital representation a digital twin provides serves as a world of its own. Within this digital world, all types of simulation can be run. It can also be used as a planning and scheduling tool for training, facility management, and the implementation of new ideas. This highlights the fact that a digital twin is a virtual environment, thus it must consist of either 2D or 3D assets or the data they produce or are expected to produce. In the modeled virtual environment, individuals can do what they choose with few limitations including the running of simulations.

Industrial cloud

Highlighting the differences between simulations and digital twins

Although the definitions of both concepts already highlight key differences, the use of case studies makes these differences more relatable. In 2019, CKE Holdings Inc., the parent company of Hardee’s and Carl Jr’s was interested in enhancing productivity levels within these facilities. The idea was to make order picking by staff easier and reduce shop floor traffic through better layout designs.

While simulations can be used to analyze the shortest distance between workstations or the effects of more storage facilities within the restaurant, a digital twin can do much more. Using a digital twin, CKE Holdings Inc. was able to recreate digital representations of existing shop floors and run multiple simulations, design, and scheduling ideas to enhance productivity. This resulted in improvements in every aspect of the facility’s operation from staff training, scheduling, and meeting customer demands more efficiently.

This shows that while simulations may help with understanding what may happen when changes are introduced, a digital twin helps with understanding both what is currently happening and what may happen within a process. Some key differences include:

Real-time simulations – Traditional simulations are run in virtual environments that may be representations of physical environments but do not integrate real-time data. The regular transfer of information between a digital twin and its corresponding physical environment makes real-time simulation possible. This increases the accuracy of predictive analytical models and the management and monitoring policies of enterprises.

Enhancing product design – Advanced simulations have the capacity to analyze thousands of variables to provide diverse answers, but a digital twin can be used to achieve more. Boeing’s integration of digital-twin technology in aircraft design and production is an example of its capabilities. In this case, a digital twin was used to simulate parts of an aircraft to analyze how diverse materials will fare throughout the life-cycle of the aircraft. With these calculations, Boeing was able to achieve 40% improvement in the quality of certain parts it designed.

Optimize real-world products and processes – Every Tesla automobile running today has a digital twin that captures the large data sets each car produces. The captured data is used in optimizing design, predictive analytics, enhancing self-driving initiatives, and maintenance. This highlights how a digital twin immediately or directly affects the physical entity it represents unlike the theoretical results simulations provide.

Conclusion 

Regardless of the path taken, the digital transformation of assets and processes enhances industrial effort in many ways. This includes refining product design, real-time troubleshooting, and implementing new ideas. To achieve a comprehensive digital transformation of existing or planned entities, systems, and processes, accurate data capture is required. Enter smart edge technology or devices.

The accuracy of a simulation or a digital twin relies heavily on the accuracy of the data used in designing its models. In today’s shop floors, data capture is being made possible by smart edge device and human-machine interfaces and only with these types of data can a digital transformation occur. ... '

UN: Global Computer Simulation Tool

Quite a considerable simulation is proposed.    Would be difficult to do, depending on the breadth and context involved.   Perhaps a realm where agent based modeling might be applied to simplify some aspects., which we aimed to do in regional models.  Various predictive models could be used to drive aspects of the model.  Investments are mentioned as drivers.  Legal system as constraints.   Risk could be included to understand aspects of events like pandemics.  But all this is still hard to do accurately.

UN: Computer Simulation Tool Could Boost Global Development
Technology Review in CACM
May 29, 2020

The United Nations is backing a new computer simulation tool that could help governments boost sustainable development and address global challenges. The Policy Priority Inference (PPI) software employs agent-based modeling to predict and simulate what would happen if policymakers invested in one project rather than another, informing the simulation with economics, behavioral science, and network theory. PPI allocates funding to "bureaucrats" who spend their apportioned money on different projects, then applies data about government budgets, the historical impact of spending on past policies, the effectiveness of a country's legal system, and estimated losses due to known inefficiencies. The software then suggests which policies are most worthy of investment. The goal is to help policymakers understand the wider ramifications of their decisions.  ... "

Anomaly Response: How we Respond to the Unexpected

Intriguing piece.   Made me think of our current predicament as well.    Can we model human adaptation to expected and unexpected events?   I like the notion of exploring different responses.  Would add then we could simulate them via a properly an agent or twin model.  Technical article.

Cognitive Work of Hypothesis Exploration During Anomaly Response
A look at how we respond to the unexpected
Marisa R. Grayson in Queue ACM

Web-production software systems operate at an unprecedented scale today, requiring extensive automation to develop and maintain services. The systems are designed to adapt regularly to dynamic load to avoid the consequences of overloading portions of the network. As the software systems scale and complexity grows, it becomes more difficult to observe, model, and track how the systems function and malfunction. Anomalies inevitably arise, challenging incident responders to recognize and understand unusual behaviors as they plan and execute interventions to mitigate or resolve the threat of service outage. This is anomaly response.1

The cognitive work of anomaly response has been studied in energy systems, space systems, and anesthetic management during surgery.9,10 Recently, it has been recognized as an essential part of managing web-production software systems. Web operations also provide the potential for new insights because all data about an incident response in a purely digital system is available, in principle, to support detailed analysis. More importantly, the scale, autonomous capabilities, and complexity of web operations go well beyond the settings previously studied.7,8

Four incidents from web-based software companies reveal important aspects of anomaly response processes when incidents arise in web operations, two of which are discussed in this article. One particular cognitive function examined in detail is hypothesis generation and exploration, given the impact of obscure automation on engineers' development of coherent models of the systems they manage. Each case was analyzed using the techniques and concepts of cognitive systems engineering.9,10 The set of cases provides a window into the cognitive work "above the line" (see "Above the Line, Below the Line" by Richard Cook in this issue) in incident management of complex web-operation systems (cf. Grayson, 2018).  .... "

Bayer's use of Digital Twins, Decision Science

Another example of AI and Digital Twins being used to construct virtual models at major enterprises.

Bayer uses digital twins to reshape business strategy
Bayer Crop Science has created 'virtual factories' to provide dynamic digital representations of the equipment and processes for each of its nine North American corn seed manufacturing sites.
     By  Thor Olavsrud in CIO

For the past several years, Bayer Crop Science has been working to embed decision science into every facet of its business, from logistics to genetic sequencing. The strategy, driven by machine learning and artificial intelligence, now includes digital twins, or "virtual factories," that model each of the nine corn seed manufacturing sites that Bayer operates in North America.   ... " 

Digital Twins for Urban Planning

Reminds me of the urban/city planning games like SimCity.   And then also the Agent Models we used to construct simulations of very complex country spaces.  The Digital Twin idea allows us to further specify the details of the participants,  which was hard in the past methods.   But are we aiming to optimize or just explore?

Digital Twins Give Urban Planners Virtual Edge
By Financial Times in CACM

Showing the interrelationships of municipal activities and the data they generate.
Digital twins give a city's planners, policymakers, resource managers, asset owners, and  
Digital twins—virtual simulations of cities—give urban planners, policymakers, resource managers, asset owners, and citizens the advantage of more dynamic tools and information, which can benefit new construction and traffic management, and provide tools for residents to explore the effects of planned projects.

One example is Glasgow, Scotland's Future City project: the initiative's tools offer citizen-accessible data on sustainability overlaid on interactive maps, customized dashboards with widgets on environmental conditions, and data on seasonal food availability.

Meanwhile, Cambridge University's National Digital Twin Project created a U.K. network of city-scale digital twins, with guiding principles that prioritize trust, transparency, social value, ownership, responsibility, and security.

Neil Thompson at engineering company Atkins Global said, "Digital twins offer new opportunities for sustainability and wellbeing—from a physical and a psychological perspective." ..... "

Virtual Agents

A broader take than chatbots, more addressed to solving specific customer service issues.    We used the term in loose combination with agent-models to deliver goal-specific assistants.     Was always important to have very specific goals to drive their actions.  Usually using simulation style prediction.   But we often used simpler methods when appropriate.    The definitions online vary.   A number of vendors now talking this are covered in this article.

No, IBM is not the only relevant player in virtual agents
  by Matt Marshell

Last month, IBM General Manager of Data and Watson AI, Rob Thomas, told VentureBeat that IBM was the only major enterprise provider in the red-hot area of virtual agents.

Virtual agents are software that can chat with customers through text, voice, or web chat. “There really are no big players, except for us,” Thomas said at the time. He called the rest of the virtual agent providers “fireflies,” because they are small and there are so many of them..... "

Agent Based Mesa Models in Python

This is new to me.    We actively used agent models for consumer interaction understanding.  See agent tag for more.

Introduction to Mesa: Agent-based Modeling in Python
Ng Wai Foong

Python-based alternative to NetLogo, Repast, or MASON for agent-based modeling

Simulation result showing segregation between blue and red agent

Agent-based modeling relies on simulating the actions and interactions of autonomous agents to evaluate their effects on the system. It is often used to predict the projections that we will obtain given a complex phenomena. The main purpose is to obtain explanatory insight on how the agents will behave given a particular set of rules. Agent-based modeling has been extensively used in numerous industry such as biology, social sciences, network and business. This article covers the necessary steps to kick-start your agent-based modeling project using an open-source python module called Mesa. There are 4 sections in this tutorial:   ... " 

360 Degree AI Agent View

Intriguing idea.   Many applications to maximize information.  Although also likely a distraction as well. Like the idea of an 'Agent' being beyond a person with that role, but also any kind of information gathering system, human or not.

Glimpses' Give AI Agent 360-Degree View   in Futurity.org   By Marc Airhart

University of Texas at Austin (UT Austin) researchers have developed an artificial intelligence (AI) system that can take a few quick glimpses of an area and infer its whole environment. The researchers used deep learning to train the AI agent on thousands of 360-degree images of different environments. When presented with a scene it has never seen before, the system uses its experience to choose a few glimpses that together add up to less than 20% of the full scene. Based on these glimpses, the agent infers what it would have seen if it had looked in all the other directions, reconstructing a full 360-degree image of its surroundings. Said UT Austin researcher Santhosh Ramakrishnan, "Using extra information that's present purely during training helps the [primary] agent learn faster." .... '

China to Use AI for Diplomatic Strategy

Quite intriguing, pointers to more technical background or details?    Will gaming be an element?  Certainly simulation.  Recall we used agent based methods to simulate Chinese retail changes. (See link to Agent Model examples in tags below)

Artificial intelligence, immune to fear or favour, is helping to make China’s foreign policy  By Stephen Chen in the South China Morning Post

The programme draws on a huge amount of data, with information ranging from cocktail-party gossip to images taken by spy satellites, to contribute to strategies in Chinese diplomacy.

Attention, foreign-policy makers. You will soon be working with, or competing against, a new type of robot with the potential to change the game of international politics forever.

Diplomacy is similar to a strategic board game. A country makes a move, the other(s) respond. All want to win.

Artificial intelligence is good at board games. To get the game started, the system analyses previous play, learns lessons from defeats or even repeatedly plays against itself to devise a strategy that can be never thought of before by humans. ....  " 

Digital Twins for Personalized Medicine.

Reminds me in the human sense of agent based models.   And their use to address group behavior. Interesting, but not necessarily predictive.   The article quotes George Box, who said  'All Models are wrong, some are useful'.    How correct will the models be, how useful?   We expect personal accuracy from medicine.  Worth examining.

Digital Twins for personalized medicine: promising, with caveats    By Neil Raden  in SiliconAngle

" ... Digital Twins, a concept from the “industrial internet of things” or IIoT, is the discipline of devising highly capable simulation models, especially those that consume streaming data from sensors to anticipate maintenance issues, impending failure of components and improving performance. In terms of the degree of difficulty of modeling, Digital Twins for IIoT machines such as jet engines, oil wells and wind turbines are actually at the lower end as they employ detailed knowledge of the engineering of the objects. These Digital Twins may be quite complex, but because they are well-understood, the models are more likely to be useful.

Devising a simulation model of human behavior, such as the classical propensity models, is much more difficult because humans are so unpredictable and engineering approaches obviously don’t apply. In effect, these models may do a good job of predicting propensity based (on) many criteria, but at any given moment for any given individual, their predictive capability is quite low.  .... " 

Modeling the Visual Intelligence of Dogs

Quite a remarkable claim.   Can many visuals replace the ability to query a system about about what it knows.  Could this work with humans, entities like firms and their data?  Examining.

Via the University of Washington and Allen Institute for AI.  Who used neural networks to understand the behavior of dogs.   And suggest that animals provide data to train AI systems, including robotics.  What other visual agents?  And how accurate is the model?  Examining.

Who Let The Dogs Out? Modeling Dog Behavior From Visual   in arXIV
Kiana Ehsani, Hessam Bagherinezhad, Joseph Redmon, Roozbeh Mottaghi, Ali Farhadi

We introduce the task of directly modeling a visually intelligent agent. Computer vision typically focuses on solving various subtasks related to visual intelligence. We depart from this standard approach to computer vision; instead we directly model a visually intelligent agent. Our model takes visual information as input and directly predicts the actions of the agent. Toward this end we introduce DECADE, a large-scale dataset of ego-centric videos from a dog's perspective as well as her corresponding movements. Using this data we model how the dog acts and how the dog plans her movements. We show under a variety of metrics that given just visual input we can successfully model this intelligent agent in many situations. Moreover, the representation learned by our model encodes distinct information compared to representations trained on image classification, and our learned representation can generalize to other domains. In particular, we show strong results on the task of walkable surface estimation by using this dog modeling task as representation learning. ..."

Integrating Agent Models with Process Models

In a conversation on modeling today the topic of 'Agent Based Modeling (ABM)' came up.     And it had come to mind that such ABM models could also be usefully integrated with process models.  The ABM modeling the architecture of useful agent interaction, suitable for simulation, and a Process model simulating the sequential march towards a goal.   Has this integration been considered by anyone as a useful approach?    See past writing here on Agent models, based on work in 2012, which we used successfully to understand consumer and group behavior in retail.   We included process goals, but not formally, nor predictively in the model.

Chinese Economics

Been looking at the 'One Belt, One Road Initiative'.  Earlier we had looked at modeling retail demand in Chinese markets using agent simulation modeling, as it predicted future supply chains.    See china tag and 'Agent Models' below.  This Wharton view is of interest. Continuing to examine.

Will President Xi Jinping Let Markets Decide China’s Future?

China’s twice-a-decade Communist Party congress wrapped up on October 26 with party head and President Xi Jinping claiming a place alongside revolutionary leader Mao Tse-tung in the pantheon of modern Chinese heroes. In addressing the congress, Xi focused on contradictions the party faces in steering China toward a brighter future, much as Mao highlighted “class contradictions” decades earlier.

But the party gathering did little to clarify how the leadership plans to handle the challenges simmering within the world’s second-largest economy, and especially within its chaotic financial system.

Franklin Allen, an emeritus Wharton professor of finance, and a professor of finance and economics at Imperial College in London, questions Xi’s appetite for painful reforms that are needed to rebalance China’s economy away from its longtime heavy reliance on construction investment and exports. “Xi has established tremendous political power. Now the question is how much of that he will turn into economic reforms,” Allen says. For now, Xi seems to prefer using his “One Belt, One Road Initiative,” to expand Chinese supply chains and market access, as well as its geopolitical influence, across the developing world. In the meantime, on the domestic front, “I would not be surprised if there was slow and gradual reform.” .... "  

Models of China Ambitions and Directions

Wharton has published a special, multi segment piece on new China Strategy and Economics.  We did lots of work trying to understand the direction of China using advanced agent models.  Often touched upon in this blog.     This article touches on many of our interests, including infrastructure, retail, manufacturing, supply chain strategy and beyond.   At a high level, but valuable for its setting the stage.   The below piece is one example, lots more pointed to at the link:

China: New Ambitions, New Directions

" ... China’s “One Belt, One Road” initiative, for example, would stitch together roads, ports, railways and other links from East China through Southeast, and South and Central Asia over to Europe. It exceeds in scope the Marshall Plan that rebuilt post-war Europe. Beyond that, China is by far the biggest source of financing for many of its neighbors. The Export and Import Bank of China alone lent $80 billion in 2015, compared with $27 billion from the Asian Development Bank. All this expands China’s economic and geopolitical sway across Asia, the Middle East, Europe and Africa. .... " 

Home Automation Virtual Agent

Interesting approach that I had not seen .... highlighting the Watson conversation service.

Build a Home Automation Virtual Agent on Bluemix

With the home automation trend growing, have you wondered how you could build your own home automation virtual agent on Bluemix? Check out this blog post to see how a PubNub developer used PubNub BLOCKS and Watson Conversation to do it.
 by: Shyam Purkayastha

Man’s desire to be a part of the social ecosystem has led to the invention of many communication and information sharing tools. This trend is now morphing to include use cases where we interact with non-living things, as well. Let’s look at one such application where we can communicate with our things through chat, just like way we would Whatsapp our family and friends.

Home automation is an ubiquitous application. We talk to our appliances, and they obey our orders. That is so cool! But let’s take it a step further. We’ll want to make it a bit more seamless, so that we talk to our home in a natural conversation. But how do we do it? Machines talk in binary code which is cumbersome for humans. In this blog article, we will show you how to build a home automation app. So follow along and check out the demonstration provided later in this article to help you understand how to build a virtual assistant for your home. .... 

Watson Conversation service provides a drag and drop dialog builder. This dialog builder is the key to designing dialogs that are intuitive for human users and, at the same time, can be deciphered by machines.

A typical human-to-machine conversation is very different from human-to-human conversation. Machines do not usually engage in a conversation flow like we humans do. They take commands and respond with an action. The Watson Conversation service allows us to build specific dialogs that convey commands and actions between humans and machines. The image below illustrates how this is achieved via intents and entities:  .... " 

Knowledge Engineering Book for Cognitive Assistants

So how do you actually engineer knowledge to integrate into an assistant system? Its a mix of knowledge architecture, reasoning and effective delivery.  Many of our early attempts struggled with the idea. This book takes a look at approaches.  I will be reviewing.  From GMU.

Knowledge Engineering: Building Cognitive Assistants for Evidence-based Reasoning    Authors: Gheorghe Tecuci, Dorin Marcu, Mihai Boicu, David A. Schum
Hardcover: 456 pages
Publisher: Cambridge University Press (September 2016)
ISBN: 9781107122567

This book presents a significant advancement in the theory and practice of knowledge engineering, the discipline concerned with the development of intelligent agents that use knowledge and reasoning to perform problem-solving and decision-making tasks. It covers the main stages in the development of a knowledge-based agent: understanding the application domain, modeling problem solving in that domain, developing the ontology, learning the reasoning rules, and testing the agent. The book focuses on a special class of agents: cognitive assistants for evidence-based reasoning that learn complex problem-solving expertise directly from human experts, support experts, and nonexperts in problem solving and decision making, and teach their problem-solving expertise to students. A powerful learning agent shell, Disciple-EBR, is included with the book, enabling students, practitioners, and researchers to develop cognitive assistants rapidly in a wide variety of domains that require evidence-based reasoning, including intelligence analysis, cybersecurity, law, forensics, medicine, and education.  .... " 

Discussion in Cognitive Systems Institute,  Linkedin.

Bots Fighting Online

The Growing Problem of Bots That Fight Online

The way software agents interact on the Web is poorly understood. Now evidence shows that they fight each other for years.

by Emerging Technology from the arXiv  September 20, 2016

Software agents, or bots, permeate the Web. They gather data about Web pages, they correct vandalism on Wikipedia, they generate spam and even emulate humans.

And their impact is growing. By some measures, bots account for 49 percent of visits to Web pages and are responsible for over 50 percent of clicks on ads. This impact is set to increase as the number of bots rises exponentially.

“An increasing number of decisions, options, choices, and services depend now on bots working properly, efficaciously, and successfully,” say Taha Yasseri and pals at the University of Oxford in the U.K.  “Yet, we know very little about the life and evolution of our digital minions.”

This raises an interesting question. How do bots interact with each other? And how do these interactions differ from the way humans interact?  ... " 

Designing Social Interactions in a Teachable Agent

This a reminder about our Cognitive Systems Institute Group Speaker Series this week, Thursday, September 22, 2016 at 10:30 am ET US (9:30am CT, 7:30 am PT).  Our presenter this week is Erin Walker from Arizona State University, who will be presenting "Designing Social Interactions in a Teachable Agent."    Slides.  Recording.  ...

  A link to slides and a recording of each call should be available on the CSIG website 
(http://cognitive-science.info/community/weekly-update/).   We encourage those who join the calls to add questions and comments to the LinkedIn Discussion Group https://www.linkedin.com/groups/Cognitive-Systems-Institute-6729452  .... 

Also, want to let you know that IBM will have a presence at two upcoming conferences:   World of Watson in Las Vegas starting with an Academic Workshop in Cognitive and Data Science on October 23 (Conference 10/24-27) and Educause in Anaheim, CA October 25-28.   Let me know if you would like more information on registration costs and agendas.

Dianne Fodell

IBM Global University Programs
fodell@us.ibm.com

What Does it Mean for Everything to be Smart?

What are the challenges for invention on the Internet of Things?  In the early days of our use the only application was an indicator of what a thing was.  So it could be counted, located, or paid for. Now the possibilities have grown, and we expect many very complex things to take their place on the net and start conversations with other things that are there.    How do you innovate on the IoT?  Would seem a place ready for the use of agent models.

Accenture Builds a Virtual Assistant called MyWizard

Continued efforts to build virtual assistants.  Named MyWizard.    Note the industry specific elements and knowledge.  How much local learning?    I like the statement of it dealing directly with business outcomes.   Looking further.  Can I get a demo?

Accenture Launches Intelligent Automation Platform to Deliver Smarter, More Efficient Application Services that Improve Business Outcomes  .... " 

The intelligent automation platform, Accenture myWizard, augments human technologists with virtual agents powered by artificial intelligence, armed with analytics capabilities and the ability to tap Accenture’s vast technology and unique industry knowledge  .. " 

" .... The platform is able to mine Accenture’s vast, cumulative knowledge base of vertical industry operating models, process flows and key performance indicators, giving Accenture myWizard a unique set of business domain experience that can identify and support tangible business results. Hosted on Microsoft Azure, Accenture myWizard’s liquid, plug-and-play architecture makes it “tomorrow-proof” with the ability to add in new capabilities as artificial intelligence matures. .... " 

List of Virtual Assistants covered.