SmartResource: Proactive Self-Maintained Resources in Semantic Web TEKES Project proposal

Download Report

Transcript SmartResource: Proactive Self-Maintained Resources in Semantic Web TEKES Project proposal

SmartResource:
Proactive Self-Maintained
Resources in Semantic Web
TEKES Project proposal
Vagan Terziyan, Project Leader
Industrial Ontologies Group
Agora Center, University of Jyväskylä
Our Team and Consortium
University of Jyväskylä
Industrial Ontologies Group (SmartResource)
“Industrial Ontologies” Group: http://www.cs.jyu.fi/ai/OntoGroup/index.html
SmartResource: Project Proposal
2 of 21
Networked Business Environments
Some purposes of NBE development :
•
knowledge management:

•
knowledge business:

•
•
mining, accumulation and sharing of expert
knowledge within the whole enterprise
deliver gained
external market
enterprise
experience
new (value-added) services and
solutions
integrated business solutions
to
“In a networked business environment Metso will be
a business hub controlling the flow of information in
the network of installed Metso devices and solutions,
and Metso’s customers and partners.” (Future Care)
Semantic Web technology provides standards for metadata and ontology development
such as semantic annotations (Resource Description Framework) and knowledge
representation (Web Ontology Language). It facilitates interoperability of heterogeneous
components, authoring reusable data and intelligent, automated processing of data.
Semantic Web is an enabling technology for the future Networked Business
Environment
SmartResource: Project Proposal
3 of 21
Bringing New Value to the Data

Reusing data

Sharing data

Integrating data
in
Emerging Semantic Web application areas:
 Knowledge Management
 e-Business
 Enterprise Application Integration
Networked Business Environment requires new advanced ways of data and
knowledge management
Industrial Maintenance domain is a good application case for the concept of the
Networked Business Environment
Networked Maintenance Environment will bring all benefits of the knowledge
management, delivering value-added services and integration of businesses
SmartResource: Project Proposal
4 of 21
PROJECT WIDER OBJECTIVE
- to combine the emerging Semantic Web,
Web Services, Peer-to-Peer, Machine
Learning and Agent technologies for the
development of a global and smart maintenance
management environment, to provide Webbased support for the predictive maintenance of
industrial devices by utilizing heterogeneous and
interoperable Web resources, services and
human experts
Tekes Project Application, Submitted January 2004
Industrial Resources
Classes of resources in maintenance systems:
•
•
•
Devices - increasingly complex machines, equipment,
etc., that require costs-demanding support
Processing Units (Services) – embedded, local and
remote systems, for automated intelligent monitoring,
diagnostics and control over devices
Humans (Experts) – qualified users of the system,
operators, maintenance experts, a limited resource
that should be reused
SmartResource: Project Proposal
6 of 21
MAIN RESEARCH OBJECTIVE
GUN
Global
Understanding
eNvironment
SmartResource: Project Proposal
Our intention is to provide
tools and solutions to make
heterogeneous
industrial
resources (files, documents,
services, devices, processes,
systems, human experts, etc.)
web-accessible, proactive and
cooperative in a sense that
they will be able to analyze
their state independently from
other systems or to order such
analysis from remote experts
or Web-services to be aware of
own condition and to plan
behavior towards effective and
predictive maintenance.
7 of 21
Smart Maintenance Environment
“Experts”
“Devices with
on-line data”
“Services”
SmartResource: Project Proposal
8 of 21
Project Objectives (Year 1)
Define Semantic Web-based framework for unification of
maintenance data and interoperability in maintenance system
Research and Development:
•
Resource State/Condition Description Framework (RSCDF) based on
Semantic Web and extension of RDF (Resource Description Framework)
“Expert”
•
RSCDF adapters (wrappers)
for devices, services and experts:
- browsable devices
- application-expert interface
- RSCDF-enabled services
SmartResource: Project Proposal
“Device”
RSCDF
“Service”
9 of 21
Project Objectives (Year 2)
Development of agent-based resource management
framework and enabling meaningful resource interaction
•
Adding agents to resources
•
•
•
Enabling resource proactive
behavior. Designing
Resource Goal/Behavior
Description Framework (RGBDF - Lite)
Designing agents to maintain
resources (RGBDF Engine)
“Expert”
Resource
Agent
”Adapter”
Smart Maintenance
Environment
Implementation of agent-communication scenarios “Expert”
•
•
service learning
remote diagnostics
“Service”
“Device”
“Device”
Lite
Remote
diagnostics
Expert ~ Service
“Service”
Service learning and
remote diagnostics
SmartResource: Project Proposal
10 of 21
Project Objectives (Year 3)
Development of networked maintenance environment
•
Development of P2P agent-communication system
•
•
•
•
Research of the Resource Goal/Behavior Description Framework
•
•
•
Resource Discovery
Maintenance Data & Knowledge Integration
Certification and credibility assessment of services
Semantic modelling of a resource proactive behaviour
Exchanging & integrating models of resource (maintenance) behaviour
Testing “on-the-field” using
•
•
•
Real devices
Existing diagnostic software as Web-services
Experts
SmartResource: Project Proposal
11 of 21
Maintenance Networking Environment
“Expert” Network
“Device” Network
Labelled
data
Resource
“Expert”
Agent
History
data
Labelled
data
RSCDF
data
Resource
Agent
“Device”
“Embedded
Sensor data Alarm Service”
results
”Adapter” RSCDF
data
”Adapter”
User
interface
Remote Expert Platform
Labelled
“RSCD Alarm
Sensor data
”Adapter” RSCDF Service”
data
“Service”
Resource
Agent
Local (Embedded) Platform
Diagnostic
model
“Service” Network
RSCDF
data
”Adapter”
Learning
process
Remote Service Platform
SmartResource: Project Proposal
12 of 21
P2P networking
- network of hubs
- highly scalable
- fault-tolerable
- supports dynamic changes
of network structure
Why to interact?
1.
2.
3.
4.
5.
- does not need
administration
Resource summarizes “opinions” from multiple services;
Services “learns” from multiple teachers;
One service for multiple similar clients;
Resources exchange lists of services;
Services exchange lists of clients.
SmartResource: Project Proposal
13 of 21
Integrating services
Evaluation and
Result integration
mechanism
w1
w2
“Device”
Device will support service
composition
in
form
of
ensembles using own models of
service
quality
estimation.
Service composition is made with
goal of increasing diagnostic
performance.
w5
w3
w4
Labelled
data
Learning
sample
Test sample
“Service”
“Service”
Diagnostic
model
…
Diagnostic
model
SmartResource: Project Proposal
14 of 21
Integrating knowledge
“Service”
Service builds classification model; many
techniques are possible, e.g.:
• own model for each device;
• one model from several devices of the same
type (provides device experience exchange) .
Device-specific
diagnostic model
Diagnostic
model
1
…
n
Device Class-specific
diagnostic model
“Device”
Labelled
data
“Device”
Labelled
data
“Device”
Labelled
data
SmartResource: Project Proposal
Diagnostic
model
“Device”
“Device”
“Device”
…
Labelled
data
Labelled
data
Labelled
data
15 of 21
Certification
Sure, there are security threats as in
any open environment. Security is to be
ensured using existing solutions for
Internet environment.
Existence of certification authorities
is required in the network. Certificates
gained by services and trust to the
certificate issuer are factors that
influence optimal service selection. The
quality of service is evaluated by users
as well.
Service 1
Service 2
Service 3
5
3
4
Device
1
2
Certifying
party
SmartResource: Project Proposal
6
Own
evaluations
16 of 21
Development Stages
Project will produce 3 versions of prototype software by
implementing the following components and functionality:
Year 1: Resource Adapters to the RSCDF-based unification of resource
data; Remote resource access in Semantic Web environment
Year 2: Resource Agents for remote diagnostics; Learnability of services
Year 3: Support for semantic P2P networking and diagnostic services
integration
SmartResource: Project Proposal
17 of 21
Project Results
P2P environment that integrates many
devices, many services, many human experts
and supports:
Adaptation of resources (devices,
services, experts) to the Environment
Unification of
maintenance data
Discovery of necessary network
components using their profiles
Service
Interaction ”One service – many devices”
Support for services
that are able to learrn
Resource
Agent
Research Results:
Interaction ”One device – many services”
SmartResource: Project Proposal
RSCDF
RGBDF
Proactive Resources
P2P Maintenance
18 of 21
New partners
…are warmly welcome!
SmartResource: Project Proposal
19 of 21
Obtain More Information about
SmartResource from:
Head of SmartResource Industrial Consortium
(Steering Committee Head) Dr. Jouni Pyötsiä,
Metso Automation Oy.
[email protected] , Tel.: 040-548-3544
SmartResource Contact Person Prof. Timo Tiihonen,
Vice-Rector, University of Jyväskylä
[email protected] , Tel.: 014-260-2741
SmartResource Project Leader Prof. Vagan Terziyan,
Agora Center, University of Jyväskylä
[email protected] , Tel.: 014-260-4618
SmartResource: Project Proposal
20 of 21
Obtain More Information about
SmartResource from:
Presentation of our group:
http://www.cs.jyu.fi/ai/OntoGroup/IOG_Presentation.ppt
Sample of presentation of our SmartResource project activities:
http://www.cs.jyu.fi/ai/Madeira.ppt (in text: http://www.cs.jyu.fi/ai/Smart_Resource.doc )
Some relevant research papers of our group:
http://www.cs.jyu.fi/ai/Mobile_Components.doc
http://research.i2r.a-star.edu.sg/iaamsad/ijcss/Journals/Vol4No2/2003-2-terzijan-5.PDF
http://www.cs.jyu.fi/ai/papers/IJWSR-2004.pdf
More papers of our group:
http://www.cs.jyu.fi/ai/vagan/papers.html
Web sites of our group with more information:
http://www.cs.jyu.fi/ai
http://www.cs.jyu.fi/ai/OntoGroup
SmartResource: Project Proposal
21 of 21