Upload
others
View
1
Download
0
Embed Size (px)
Citation preview
• Lista
• Lista
• Lista
• Lista
• Lista
Aalto Industrial Internet Campus
Jari Juhanko
COO, AIIC
Aalto UniversityInnovation and
Encounters backed up by Research and
Education
• Lista
• Lista
• Lista
• Lista
• Lista
Bio
TkT Jari Juhanko, Aalto-yliopistoCOO, Aalto Industrial Internet Campus, http://[email protected], +358 50 556 3564
Koneenrakentaja, mekatroonikko
Suunnittelu, valmistus ja kunnossapito
Industrial Internet realisti
Professori 2008…2013, tutkimuspäällikkö, tutkija
Roll Dynamics Engineering Oy, CEO, 1999 – 2001
Rollresearch Intl Oy, hallitus 2001 – …
• Lista
• Lista
• Lista
• Lista
• Lista
Bio
TkT Jari Juhanko, Aalto UniversityCOO, Aalto Industrial Internet Campus, http://[email protected], +358 50 556 3564
Engineering design, mechatronics
Design, manufacturing and maintenance
Industrial Internet realist
Professor 2008…2013, research manager, researcher
Roll Dynamics Engineering Oy, CEO, 1999 – 2001
Rollresearch Intl Oy, board 2001 – …
• Lista
• Lista
• Lista
• Lista
• Lista
From products to system of systems
(Porter and Heppelman 2015)
• Lista
• Lista
• Lista
• Lista
• Lista
AIIC Innovation ecosystem
Aalto University in collaboration with industrial partners offer physical and digital infra for industrial internet innovation and development
Student projects and assignments require companies• to open interfaces, build APIs and act as active instructors
• to redesign the product and system architecture for collaborative R&D&I
• to study new technologies and platform economy in real pilot installation
Research projects and professional education• utilize pilot installations for testing new technologies including platform features, data governance models
and IPR security
• enable collaboration workshops with core partners and future prospects
• Lista
• Lista
• Lista
• Lista
• Lista
Research Platform for Manufacturing
Smart crane with
extensive PLM models
and IoT interfaces
IoT instrumentation for
research apparatus for
studying magnetic
bearingsExtension of NetLeap
4G/LTE/5G
infrastructure
Mindsphere IoT platform connecting
machines and physical infrastructure to
the digital world
• Lista
• Lista
• Lista
• Lista
• Lista
Aalto Industrial Internet Campus - Thematic Scope
Building and
construction
Manufacturing
industry
Process
industry
Data platform
5G for industrial internet
Business, strategy
R&D, innovation
Internet of
energy
Intelligent
mobility
• Lista
• Lista
• Lista
• Lista
• Lista
Ecosystem convergence
Competence ecosystem
Businessecosystem
Policies
Platforms
Services
Data management
Analytics
Cloud
Networking
Connectivity
Intelligence
Sensing & actuating
Assets
C CTech partner 1
Tech partner 2
Tech partner n
Service partner
Policy partner
• Lista
• Lista
• Lista
• Lista
• Lista
Digital value in the era of Industrial Internet?
Today, ”available data” cannot be utilized in daily operations
Data integrity, classification and governed distribution for differentstakeholders and different purposes are missing
• E.g. whose business is data analytics? What is the value of analytics and how therevenue is shared in the ecosystem?
• How a 3rd party company can join the ecosystem business and its digital platform?
• Lista
• Lista
• Lista
• Lista
• Lista
IT/OT Convergence
Study the challenges and implications of the foreseen convergence of 5G communications, distributed cloud computing, and CPS-oriented control systems towards a unified industrial data and computation platform
Material flow, logistics
Production equipment
On-line control & diagnostic units
Control nodes (I4.0)
Data cloud
ERP, business apps
5G
Cloud
EcosystemIndustrial
data platformFederation layer
Unified industrial data &
computation platform
• Lista
• Lista
• Lista
• Lista
• Lista
Winning recipe
open research, development &
innovation ecosystem
• Lista
• Lista
• Lista
• Lista
• Lista
Digital twin
Juuso Autiosalo
Doctoral Candidate & Project Manager
Aalto University
Working title of doctoral thesis:
Digital twin for industrial products
• Lista
• Lista
• Lista
• Lista
• Lista
Contents for the rest of the presentation
Introduction to digital twin concept
• 4 slides
Building blocks of digital twin
• 12 slides
Current activities at Aalto University and how to proceed?
• 3 slides
• Lista
• Lista
• Lista
• Lista
• Lista
Digital twin: why, what, and how? *
Why?
• “Citius, altius, fortius”: “Faster, Higher, Stronger”
What?
• Merging the digital and physical
How?
• No standard realization exists
* Contents of this slide inspired by my supervisor Kari Tammi
• Lista
• Lista
• Lista
• Lista
• Lista
Introduction to digital twin concept
There is lots of different definitions, and none of them seems to be totally wrong.
There is many different types of Digital Twins
Perhaps the most used definition:
“Digital Twin (DT)—the Digital Twin is a set of virtual information constructs that fully
describes a potential or actual physical manufactured product from the micro atomic
level to the macro geometrical level. At its optimum, any information that could be
obtained from inspecting a physical manufactured product can be obtained from its
Digital Twin.” *
* Grieves, M. and Vickers, J. (2017) ‘Digital Twin: Mitigating Unpredictable, Undesirable Emergent Behavior in ComplexSystems’, in Kahlen, F.-J., Flumerfelt, S., and Alves, A. (eds) Transdisciplinary Perspectives on Complex Systems: New Findings and Approaches. Cham: Springer International Publishing, pp. 85–113. doi: 10.1007/978-3-319-38756-7_4.
• Lista
• Lista
• Lista
• Lista
• Lista
Introduction to digital twin concept
Physical TwinDigital TwinKnowledge
Data
A short definition from one year ago, has become a bit outdated: “Digital Twin is the cyber part of a Cyber Physical System.” *
Currently, my insight is that digital twin is a cloud object that gathers together all the information that is available from a single product.
* Autiosalo, J. (2018) ‘Platform for industrial internet and digital twin focused education, research, and innovation: Ilmatar the overhead crane’, in 2018 IEEE 4th World Forum on Internet of Things (WF-IoT). Singapore: IEEE, pp. 241–244. doi: 10.1109/WF-IoT.2018.8355217.
• Lista
• Lista
• Lista
• Lista
• Lista
Physical twin vs digital twin
Physical TwinDigital TwinKnowledge
Data
1. Can be inspected through a user interface from anywhere around the world
2. Laws of physics must be simulated3. Can have artificial intelligence that can be
used to control physical twin4. Must be updated to match the physical twin
1. Can be inspected with all senses on location
2. Obeys laws of physics3. Doesn’t have
intelligence4. Is constantly changing
• Lista
• Lista
• Lista
• Lista
• Lista
Building blocks of digital twin
Datalink
Database
Identifier
Simulation model
Artificial intelligence
Physical product
Security
Userinterface
More?
• Lista
• Lista
• Lista
• Lista
• Lista
Simulation model
• Countless different alternatives: CAE, 3D or process
• Perhaps the most common example of Digital Twin!
Specific use cases:
• Digital Twin Shop-floor
• Virtual prototyping
Tao, F., & Zhang, M. (2017). Digital Twin Shop-floor: A New Shop-floor Paradigm towards Smart Manufacturing. IEEE Access. https://doi.org/10.1109/ACCESS.2017.2756069
Michael, S., & Juergen, R. (2016). From Simulation to Experimentable Digital Twins: Simulation-based development and operation of complex technical systems. In 2016 IEEE International Symposium on Systems Engineering (ISSE). https://doi.org/10.1109/SysEng.2016.7753162
• Lista
• Lista
• Lista
• Lista
• Lista
User interface
- Could be just a web site
- Different views and permissions for different users
- 3D model with AR would be nice!
Digital Twin
SalesDesign
Manufacturing
Maintenance
OutsidersOperatorhttps://blogs.windows.com/devices/2017/09/20/ford-brings-microsoft-hololens-to-design-studio-drives-speed-creativity-and-collaboration/
• Lista
• Lista
• Lista
• Lista
• Lista
Database
In many cases, just showing the data
may provide enough value.
There can be also multiple databases.
Possible contents include: Static 3D
model, Measurement data (with error
limits) Metadata/environment data,
Location, Historical data (PLM aspect)https://www.applause.com/blog/digital-twins-iot-faq/
• Lista
• Lista
• Lista
• Lista
• Lista
Identifier
- Globally unique address- Existing examples include
MAC, IP address, URL, DOI- Technologies to access the
identifier include RFID, QR code
- Can be used to access the Digital Twin
- Should be available at the ”physical twin”
• Lista
• Lista
• Lista
• Lista
• Lista
Artificial intelligence
Makes DT an active or even autonomous object.
• For reference: compare the potential of a regular car to an autonomous car.
• AI enhanced DT actively takes care of the physical product.
Use case examples:
• Analyse the condition of physical twin
• Reschedule maintenance if needed
• Trigger alarm or even stop the machine
• Lista
• Lista
• Lista
• Lista
• Lista
Security
Safe and consistent operation are minimum requirements for adopting any new
system, and DTs are no exception.
Security by design must be implemented throughout any DT
Furthermore, specific security features of DT include:
• User access management
• Update management service for the physical product
• AI based scanning of network environment
• Lista
• Lista
• Lista
• Lista
• Lista
Computation
Computation can take place in various locations:
• locally at the device
• at the edge in a gateway device
• in the cloud at some server hardware
Digital twin should orchestrate where the computation takes place depending on the time scale and computational intensity.
• Remote computing enables use of low-cost IoT devices, while local computation lowers the need for communication bandwidth
• Lista
• Lista
• Lista
• Lista
• Lista
Linking the blocks
Database
Identifier
Simulation model
Artificial intelligence
Physical product
Security
Userinterface
More?
• Lista
• Lista
• Lista
• Lista
• Lista
Linking the blocks
Datalink
Database
Identifier
Simulation model
Artificial intelligence
Physical product
Security
Userinterface
More?
• Lista
• Lista
• Lista
• Lista
• Lista
Data link
ERP
Enterprise Resource
Planning
Digital Twin
data link
IoT
equipment
PDM
Product Data
Management
CMMS
Computerized Maintenance
Management System
CRM
Customer Relationship
Management
CAE
Computer Aided
Engineering
SCM
Supply Chain
Management
ICS
Industrial Control
System
• Lista
• Lista
• Lista
• Lista
• Lista
Data link
Probably the most difficult issue because of
the multiple requirements
• APIs for IoT/M2M and connectivity
• Connection to physical twin
• Links to external databases
Basic idea proposed in:Hribernik, K. A. et al. (2006) ‘The product avatar as a product-
instance-centric information management concept’, International
Journal of Product Lifecycle Management, 1(4), p. 367. doi:
10.1504/IJPLM.2006.011055.
• Lista
• Lista
• Lista
• Lista
• Lista
DigiTwin project
The focus of the research project is in coupling the crane and its digital twin for the whole life cycle.
Physical twin
Knowledge
Data
Project builds demonstrators to prove the industrial value of digital twin concept.
Digital Twin
SalesDesign
Manufacturing
Maintenance
OutsidersOperator
• Lista
• Lista
• Lista
• Lista
• Lista
Physical world
Digital twin
Rotor Gear Motor
Simulation model Machine learning
Machine and design data
Meas. dataMetadata
Combined and verified virtual data
BEN
EFIT
Misc data
Enterprise dataWorker ID, Process, Sales data, Weather
etc.
Digital twin
Twinrotor project – combining physical models and operational data