Genius of Things: An End to End Approach to IoT with Chris O'Connor



O'CONNOR: In the words of others this morning. Wow, what a group. So, Dion gave me an assignment; he said, Chris, I want you to make Digital
Twin simple but detailed. So, here we go. Digital Twin, simple but detailed. Okay? First, we're missing a clicker. Let's go ahead and roll a little video here. Digital twin is the ability to take a virtual
representation of the elements and the dynamics of how an Internet of Things
device operates and works. It's more than a blueprint,
it's more than a schematic. It's not just a picture. It's a lot more than a pair of glasses. It's a virtual representation of both the
elements and the dynamics of how an Internet of Things device operates and
lives throughout its lifecycle. It's an understanding of all of its dynamics,
whether those are electrons that move or whether it's the device that's moving itself. It's about understanding the elements
that compose it and the dynamics of how that device is put together. Done correctly, a digital twin will
influence how design, build and operations of a device are constructed
in a single lifecycle. The design phase is where
engineering tooling comes together, bringing together physical
elements, physical bill of materials, pulling together virtual elements; you
heard about the software on the cars and all the different elements
and the chips that are there. Being able to coordinate and collaborate
those together into a single facility of operational oriented design that is designed
to bring out the highest quality product. In the build phase, it's about yield. It's about understanding how the devices that make the product influence the
product's tolerances and stresses and designs. And, it's about better manufacturing to drive
the correct tolerances and correct outcomes that you want to see for the
product that you're actually making. And then third, a digital twin facilitates
the actual operation of the product as well. Products age, products go through different
environments, they deal with things like weather; and, they have different
tolerances and they shift, they drift. And so your digital twin needs to drift
along with those products as they age, and that feedback when done correctly not
only facilitates the operations of the product but helps facilitate better design and better
manufacturing by the lessons that are learned and the recalibration that
takes place along the way. So, quite simply, a digital twin is a
virtual representation of the elements and the dynamics of an Internet
of Things device. It affects both the design, the build and
the operations of how products pull together. There's essential capabilities that must be
present for you to be active in a digital twin. First, you have to apply
analytics as every step. The amount of information that we're dealing
with to apply digital twin to a small device or to a complex device such as an
automobile or an aircraft is staggering. Analytics has to be both real time, it has
to be operational, it has to be quality, it has to be predictive oriented in its nature. The data that comes from a
digital twin needs to be open. You have to be able to access it
from a variety of different sources. You have to be able to pull it together into
a federated model, and you have to be able to bring it together so that you can get
that interaction, that dynamics to play. It's not just a schematic you're making. It's not just a picture you're making. You're actually making a dynamic model
that you're going to shift as you go through both the design, the
build and the operations phase with the lifecycle of that product. And then last, you're going
to apply industry context. You may actually use the same product
differently in two different industries and have two different digital twins for that
one product based on how the industry uses that product, whether it's a pump that's used in
oil and gas or whether it's a pump that's used in municipal…or, wellness and water, the
outcome is based on the industry context of how that device is going to be used. And so, a digital twin not only
captures the engineering aspects but it also captures the industry
concepts, the dynamics of how that product is used at the same time. Let's talk a little bit about
how we do this at IBM. At IBM, we start with the Watson IoT platform. It is where we bring the data
in, we connect to a variety of different data sources,
direct devices themselves. We connect to engineering capabilities. We bring data in from through partners
such as Aris from the physical side; we bring logical data in from our own
portfolio; and around the IoT platform, we start to build context of the
relationships of the information both over time and relationship to each other. Collapse and collect the information. Second, we apply cognitive insights. We operate on the data to understand its
variances and tolerances and how it's used. We apply techniques in machine to machine,
natural language processing, video, acoustical analytics and more
to help understand the dynamics of the information that you're being presented. So, when you have the information and
you have cognition taking a place on it, what you can then do — which is the third
step which is the most valuable step — is you can dynamically recalibrate
your environment. So, a digital twin, when operating
correctly, not only represents a picture, it's not only something that you can see in
glasses and explode, but it actually works to dynamically recalibrate your
environment affecting the design, the build and the operations phase of
everything you do around that particular device. Well, where can you go see one of these? It's really simple. The first place that you go see one
is go visit our own Watson IoT center. We've instrumented several of the
floors, we collect information and we apply our digital twin models across
both how we can show you dynamic recalibration around comfort, we can show it around
efficiency of how the workspace is laid out and the interactions of the different types
of office capabilities that are there. And last, we can show you the economic
impact or the environmental impact of how the representation
takes place at the same time. So, come to our IoT center. You can see our digital twin model in action. You can get your own picture of how it works and
we can talk to you about how you can apply it to your own business at the same time. With no further ado, I want to
bring up a couple special guests. First, we're going to bring up Professor Peter
Gutzmer from Schaeffler, and he's going to talk about some really interesting use cases
of digital twin inside of their business. Professor, welcome. Thank you. [ APPLAUSE ] Thank you. GUTZMER: Yes, thank you very much. Good morning from my side. I would like to start with
just a very brief question. Who from you knows who is Schaeffler? Oh, I'm amazed. I'm surprised. Schaeffler is traditional company,
mechanical industries, mobility industries. And if you were listening to what you
heard before, you know why we are here. This industry, the ecosystem that
we are in is completely changing. IoT will change the world that we are in,
and this means that we have to really move into this connection, into
these open combinations, open sources that we have told about. I'm going start, and it's really a pleasure
for me to start with a train and really, show you how we build up our ecosystem
based on the mechanical components and one of these key components
is a bearing, a roller bearing. How do we prepare this bearing for
digital trends, but it's even more. It's being connected in the
world of IoT in the future. And you heard about how important it
is in the IoT world to create data. And if you look to power trains that we have,
whether it's in cars, whether it's in windmills, whether it's in tooling machines, whether
it's in trains, there's no better place to create data of the power train behavior than
the bearing and the surrounding of the bearing. And this is what we prepared for, for showing
how we set up our structure together with IBM, with IBM Watson, to build digital grids
of the power trains that we are in and you exactly heard what we are doing. So, we are much more improving
our design phase with this, getting much more data in
about the complete system. But on the other hand, we
are looking for new services. And we can use the digital twin not
only for optimizing our R&D work, for optimizing our design work, for making
our launches being much better in that sense. No, we are really looking for new
digitized business models and they are based on these digital twins and
this is what I can show you. See the [boogie]? This is the important part of
the train where we can detect, and you heard about how important it is, for
example, the track, straightness of the track, heat, temperature, everything on the track,
so we can use the train itself, the bearing, the vibration, the forces, anything you
can think about that you can measure close to a bearing where the forces are
transmitted, where the torque is transmitted, to really sense how the machine is
working, but also how the contact between the machine and the track is working. And all this data together, together
with geographical, with thermal data, we can find out where there are
issues with a drag, for example. And this is what we are preparing
for on the one hand. On the other hand, we can then build up with the
models, with the analytics models that we have and that we use in our development
work to feed this data not with artificial load data
but with real load data. So, we can improve the design
process, but what we can do as well is really optimizing the
functional world in real time. So, we can send data about
misfunction of the track, but we can also send data about
the usage of these trains. And there's a need not only in France, but
it's all over the world — China, especially — to really run trains with speeds
up with four kilometers per hour. So, the straightness of the
track, the vibration, anything in the bearing is a connector,
force connector between the track and the machine itself in
the [vogay] that's key. And we need to collect this data. We need to use the IBM system. We need to use really the digital world
in parallel to the real world machine to the real world train to combine this
and really find solutions in realtime to stop high-speed running or to improve — this is also a key element that you
heard about — predictive maintenance. The usage of these trains is of high importance. We can send all the data about experience that
the machine had overloading, the bearing head, the grease of the content of the bearing. We can send this to the repair center
in advance and we are connecting that. Why we are doing this together with IBM? It's very clear, because we need
these cognitive availability, we need this cognitive performance to do that. And on the other hand, we need this open
source connecting with maybe SNCF, with others, and using our data cloud that we built
up in combination with the other ones, whether it's a a Bosch one,
whether it's a similar one. But based on all that, based on the
improvement is really simulating the real world with ongoing data collecting with the
artificial or with the virtual world, improving this virtual world; and
therefore, for us, data collection is one of the key elements for our future. This business model is changing
a lot, but using digital twins to optimize the whole product lifecycle is
the other key element that we are moving in. So, we are very convinced our
business model will change drastically within the next five years and we are
preparing to that, teaming up with IBM, teaming up with our clients and customers. Thank you very much. [ APPLAUSE ] O'CONNOR: Professor, thank you. Appreciate it. Thank you very much. Our next speaker is going bring in
another thing in motion: an Airbus. With no further ado, let me
introduce Axel Mauritz, come on up, talk to us about Airbus and digital twin. [ APPLAUSE ] MAURITZ: Thank you very much, Chris. So, good morning, everybody. Thanks for the invitation and to allow me to
stand here and point to some aspects which link and fit very nicely to what my
previous speakers talked already. We had heard a lot about digital twin,
and I would like to go more from that also to the strong need of the connectivity
between all the aspects of information because your companies, like all the ones
presented, face the challenges of dealing with safety critical software
intense systems and here is really, really important that these aspects are
covered from a very global perspective because otherwise we are running the
risk that we are only optimizing locally and missing the key elements of improvement. So, what is the key first for the engineer to
help them and to support them in their work? I would say this is situation awareness. The engineer, the architect, they need to
be pretty much aware of what is their part of the job they have do, so which informations
for them are relevant and reachable. What then is the thing that
they are contributing. So, they do a change. I come to an example. I will just take one of the systems
an aircraft, the deicing system. So, what I'm going to do on that and what
is the impact then to my colleagues — the other disciplines, the other systems —
to propagate this effect to understand also that when it's understood what they're doing
all together, how I really launch the actions, not only in my place, also for the others. So, let's take a look at
the deicing system example. It applies to any system we could think of. But so what we see is, okay, the deicing
system generally maybe towards explanation, it's established on the leading edge of
the wings to control the icing there. So, we want to avoid that there
is building up a lot of ice on special environmental
climatic conditions and to avoid that it impacts the flight
performance at the end of the day. So, when you look at such a system, and
you want to touch it so you need to see where you install it on the wing. Then of course it needs power
in terms of energy. If it is system which is electronically
heated or you need to provide air pressure when it's a system which physically
crushes the ice, then of course, you need to understand that there is ice or not. So, you need to have a connection
with the sensor system. You need to control the system
when it is doing what. You need to understand this in
relation to the flight control system so because the data are managed centrally
and coordinated by many different systems. So, easily come to a thousand of different
disciplines which I have a stake inside and you need to understand how
these relate to each other. Otherwise, and this is the challenge,
the operation, the work is quite slow because you face a lot of iterations. And not only that, the next problem is that
you also need that engineering time to look at all the other phases of the
lifecycle because in engineering, you want to get the product right and so you
need to understand how it behaves in operation, but that's an easy…not an
easy one but a logical one. But also in between, you need to see
how it is best efficiently manufactured. How it needs to be set up to be operable. How to pass all the tests and validations. How to maintain the system. All that needs to be understood at the
engineering time and so we are looking here for really for this connected information. So, we saw digital twins can help us
very much to look into the crystal ball when we have the right model in place so we can see how the system we
want to build is looking like. But that's not the only one; we
want also to see how it performs, how it behaves under specific context. So, therefore, deicing, the classical
one is the environmental conditions. So, here you see we need to make all the
connections and we are not talking at the end of the day about we call it always digital
twin but is many views of digital twin or we can they are called even different twins. All of them show us a part of what we need to
know but how to make sure that we don't look by accident to different systems that is
still the same, that is kept consistent. That's an important challenge which is by
all the opportunities we heard about already, maybe overlooked that to apply this
consistency, we need to have a strong backbone in understanding how all this information relate
together, are linked and connected to each other because otherwise we have no chance to
manage this in a global configuration. Because most of the technical means
we are having, having more control, they're configuration more locally,
partially tool wise or domain wise. And linking the information interrelations
allow us to come to a global configuration, and this is tremendously needed to avoid to
build not only…to build only one aircraft and not many ones which are
not fitting together. So, okay. This is what is behind then
the aspect of digital thread. So, this also something which
helps us really to benefit from this contextual linkage
navigation information. And at the end of the day, what this means in
place and IBM has a lot of enablers for that. And we did this a lot of very successful
studies on the Crystal project together with IBM colleagues, and so we are able
now to navigate even on the multisystem, multidiscipline basis through the information. Together with then the digital twins we can
understand the impact of changes in all facets and all aspects of the complete product. And by having this backbone in terms of the
information and understanding the semantics and the connections, we can provide the
consistency between these viewpoints. These are really the things which
are putting forward the development of a high-quality product but to bring
much, much more efficiency to follow better; and yes, the right first time approach. Thank you very much. [ APPLAUSE ] O'CONNOR: That's perfect. Thank you. Can I have the clicker? [ APPLAUSE ] a Thank you very much. Let's just kind of recap. Digital twin, it's virtual representation of
the elements and the dynamics of an IoT device. We've heard from Schaeffler,
we've heard from Airbus. You'll see other examples as you
listen to other speakers today talk about what a digital twin means to them. You've heard an engineering view from Axel,
you've heard a product view from Schaeffler. And a digital twin provides significant value
in terms of being able to move the lifecycle of your products through its
design, build and operate phases. With that, I want to thank you
for your time on digital twin and we'll see you around the program. Thank you. [ APPLAUSE ]

2 Comments

  1. Audrey Mciver said:

    I’ve tried to delete it and I’ve been unsuccessful at doing this. There is also 3 shared endorsement on my google account that I never authorized this I believe is a security hazard

    June 27, 2019
    Reply
  2. Audrey Mciver said:

    Digital twin I know I don’t have one and if I do it’s because of the “switch account” on my u tube account. I’ve been telling Watson that this is a hacker

    June 27, 2019
    Reply

Leave a Reply

Your email address will not be published. Required fields are marked *