SlideShare ist ein Scribd-Unternehmen logo
1 von 40
Downloaden Sie, um offline zu lesen
AI in Manufacturing
neXt LIVE with Dr. Amit Sheth
I
II
III
IV
V
VI
VII
AMIT SHETH, PhD
• Founding director of the
university-wide Aritificial
Intelligence Institute at UofSC
(AIISC)
• Core research on AI topics such as
knowledge infused learning and
neuro-symbolic computing,
• AIISC has translational research
with nearly al of the colleges at
UofSC
• Fellow of IEEE, AAAI and AAAS
Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing2
I
II
III
IV
V
VI
VII
OUTLINE
I. AIISC Introduction
II. AI in Manufacturing
III. Knowledge Graph/Ontology
IV. Computer Vision in Manufacturing
V. Predictive Maintenance
VI. NLP and Conversational AI
VII. Applications of AI in Manufacturing
Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing3
AIISC Introduction
Section I
4
I
II
III
IV
V
VI
VII
I | AIISC DRIVERS AND DISTINCTIONS
• To be recognized as the top
institution in interdisciplinary AI,
AI applications and impact in
Southeast US, and among the top
in its chosen of selected AI
subareas
● Exceptional Student Outcomes
○ Education: 20+ courses in AI
● High impact from translational
research
● Apply AI and realize impact
across the university and state
● High engagement with
communities and industry
Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing5
I
I
II
III
IV
V
VI
VII
I | UNIVERSITY-WIDE MANDATE
● College of Medicine (5)
● College of Nursing (2)
● College of Arts & Science (2)
○ Hazard & Vulnerability Res Inst
○ Institute of Mind and Brain
● College of Pharmacy
○ Colorectal Cancer
○ Digestive Inflammation Index
● College of Information & Communication
● College of Engineering & Computing
○ Civil and Environmental
○ Mechanical & Aerospace
○ Computer Sc & Engg
● College Education
○ ALL4SC
● College of Public Health
Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing6
Practically all our work involves real world challenges, real-world data, interdisciplinary
collaborators, path-breaking research and innovations, real-world deployments, real
world use, and measurable real world impact.
I
AI in Manufacturing
Section II
7
I
II
III
IV
V
VI
VII
II | BIG CHANGES IN MANUFACTURING NEED AI
● Automation supported by myriad of technologies including Robots; IoT,
Digital Twins
● Strategic changes in Supply Chain - massive disruptions, hiccups in
globalization
● Sustainability - traceability and accountability
Result: Data Tsunami -> Analytics [CAGR of 30.9% over the forecast period, 2020-
2025: ResearchAndMarkets.com]
Possible Solution: AI can help
(Recommendation/Planning/Decision Making)
[AI in manufacturing is expected to grow at a CAGR of 57.2% during 2020 and 2027:
MarketsAndMarkets.com]
Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing8
II
I
II
III
IV
V
VI
VII
II | BIG CHANGES IN MANUFACTURING NEED AI
Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing9
“Industry 4.0 is the information-intensive transformation of manufacturing (and related industries) in a
connected environment of big data, people, processes, services, systems and IoT-enabled industrial assets
with the generation, leverage and utilization of actionable data and information as a way and means to
realize smart industry and ecosystems of industrial innovation and collaboration.”
From: https://www.i-scoop.eu/industry-4-0/
II
I
II
III
IV
V
VI
VII
II | BIG CHANGES IN MANUFACTURING NEED AI
Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing10
Information is cheap.
Understanding is expensive.
Karl Fast,
Professor of UX Design,
Kent State University
AI is about converting data into
knowledge, insights and actions.
II
I
II
III
IV
V
VI
VII
II | WHAT IS EXPECTED FOR FACTORY OF FUTURE (FOF)
Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing11
1. Detect defects throughout the production process.
2. Deploy predictive maintenance to reduce downtime.
3. Respond to real-time changes in demand across the supply chain.
4. Validate whether intricate goods like microchips have been perfectly produced.
5. Reduce costs of small-batch or single-run goods, enabling greater customization.
6. Improve employee satisfaction by shifting mundane tasks to machines.
II
From: Luke A. Renner, How Can Artificial Intelligence Be Applied in Manufacturing?
I
II
III
IV
V
VI
VII
II | AI IN MANUFACTURING (WHY? -> BENEFITS)
• Direct Automation
• 24/7 production
• Safety
• Low operational cost
• Greater efficiency
• Quality control
• Quick decision making
https://www.rowse.co.uk/blog/post/7-manufacturing-ai-benefits
Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing12
https://www.industryweek.com/technology-and-iiot/article/22027119/benefits-of-
ai-on-manufacturing-a-visual-guide
II
I
II
III
IV
V
VI
VII
II | MANUFACTURING FAILURES: SEVERITY OF THE PROBLEM
Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing13
II
I
II
III
IV
V
VI
VII
II | AI IN MANUFACTURING
Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing14
“EVEN THOUGH AI HAS BECOME ONE OF THE HOTTEST TOPICS IN
MANUFACTURING TODAY, MOST MANUFACTURERS ARE AT THE
START OF THE ADOPTION CURVE. “
THOMAS LEESON
“BY THE TIME A LATE ADOPTER HAS DONE ALL THE NECESSARY
PREPARATION, EARLIER ADOPTERS WILL HAVE TAKEN
CONSIDERABLE MARKET SHARE; THEY’LL BE ABLE TO OPERATE AT
SUBSTANTIALLY LOWER COSTS WITH BETTER PERFORMANCE. IN
SHORT, THE WINNERS MAY TAKE ALL AND LATE ADOPTERS MAY
NEVER CATCH UP.”
VIKRAM MAHIDHAR & THOMAS H. DAVENPORT, HBR, DEC 2019
II
I
II
III
IV
V
VI
VII
II | AI IN MANUFACTURING
Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing15
KEY AI
SUBAREAS
Conversational
AI
Machine & Deep
Learning
Natural
Language
Processing (NLP)
Computer
Vision
Robotics
Knowledge Graph
(Ontology)
II
Knowledge Graph/Ontology
Section III
16
I
II
III
IV
V
VI
VII
III | TYPICAL NW ARCHITECTURE FOR FOF: EDGE, FOG, CLOUD
Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing17
Figure: Li et al, Online Workload Allocation via Fog-Fog-Cloud Cooperation to Reduce IoT Task Service Delay, 2019
III
I
II
III
IV
V
VI
VII
II | INDUSTRY NEXT MANUFACTURING @ MCNAIR, UOFSC
Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing18
Digital Cell
Actual Cell
II
I
II
III
IV
V
VI
VII
III | CONNECTED MANUFACTURING: SMART IOT AS SOLUTION
Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing19
III
http://wiki.aiisc.ai/index.php/Smart_Data
I
II
III
IV
V
VI
VII
III | SEMANTICS AT DEVICE AND FACTORY FLOOR NW PROTOCOL LEVELS
Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing20
Reference: Gyrard, Amelie, Pankesh Patel, Amit P. Sheth, and Martin Serrano. "Building the web of knowledge with smart iot applications." IEEE Intelligent Systems 31 (5), 2016)
P. Desai, A. Sheth, P. Anantharam: Semantic Gateway as a Service Architecture for IoT Interoperability, 2015.
● Moving computation and intelligence closer to data generation.
● Semantic Gateway as a service for interoperability between devices
that are using different protocols.
III
I
II
III
IV
V
VI
VII
III | DATA INTEROPERABILITY
Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing21
III
I
II
III
IV
V
VI
VII
III | ANALOGY WITH HUMAN HEALTH
Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing22
III
I
II
III
IV
V
VI
VII
III | TYPES OF INTEROPERABILITY
Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing23
Interoperability of
● NWs & protocols
● Data
Data interop:
● Domain
independent
● Domain specific
SenML, SSN
Semantic annotation
Liu et al, Device-Oriented Automatic Semantic Annotation in IoT, 2017
III
I
II
III
IV
V
VI
VII
III | ROLE OF ONTOLOGY/KG FOR INTEROPERABILITY: SSN
Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing24
Semantic annotation/
labeling help with shared
meaning/uniform
interpretation
of data
SSN ontology
provides framework for
semantic annotation of
sensor/device data;
Similarly application/
domain specific
ontology/knowledge graph
can support semantic
annotation wrt to the
application/domain/task
III
I
II
III
IV
V
VI
VII
III | DIKW: DATA, ANNOTATION, ABSTRACTION, ACTION
Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing25
Adapted from: Gyrard, et al,
Building the Web of Knowledge with Smart IoT Applications (Extended Version), 2016
ISA 95
model
III
I
II
III
IV
V
VI
VII
III | FACTORY OF FUTURE (FOF) NETWORKING
Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing26
Intizar Ali, Pankesh Patel, John Breslin, “Middleware for Real-Time Event Detection and Predictive Analytics in Smart Manufacturing”, 15th International Conference on
Distributed Computing in Sensor Systems (DCOSS), 2019.
III
I
II
III
IV
V
VI
VII
III | USE OF KNOWLEDGE GRAPHS IN SMART MANUFACTURING
Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing27
VISUAL SENSORS
Security Cameras, Drones,
Inspection Cameras
PHYSICAL SENSORS
INDUSTRIAL SENSORS
Load cell, Accelerometer,
Optical sensor, Potentiometer,
RTD temperature sensor
HEAT MAP SENSOR
Infra-Red heat map sensor
DIGITAL TWIN
Factory Configuration
Process simulators
Loops
Manufacturing Process
Manufacturing Knowledge
Representation
MANUFACTURING ONTOLOGY
MANUFACTURING KG
Downstream Tasks
ADAPTIVE KG UPDATE MODULE
Calculating
Ont. + KG
update
MANUFACTURING SCENE/ EVENT
UNDERSTANDING
FAULT DETECTION
Events
Features of Interests
Computer Vision + Signal
Processing Module
KG facts extraction
and infusion
Enhanced Fault
Detection
Feedback
III
I
II
III
IV
V
VI
VII
III | REVISITING ARCHITECTURE: DATA TO ABSTRACTION
Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing28
III
Computer Vision in Manufacturing
Section IV
29
I
II
III
IV
V
VI
VII
IV | COMPUTER VISION EXAMPLES IN FOF
• Predictive maintenance of machinery: Using IoT sensors to monitor the
production line in real-time to reduce unscheduled downtime and increase
productivity
• Inspection of defectives: Monitor the assembly lines and identify the
defective components
• Accurate assembly of components: Alert system for misassembly or mid-
operation failure.
• Quality control for products: Eg: Acquire Automation implements machine
vision that permits manufacturers to inspect bottles in a complete 360-
degree view to verify that products are placed in the correct packaging
• Health and safety: Deep learning-based AI to track the movement of people
and predict where the machines are going to be to avoid dangerous
interactions
Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing30
IV
I
II
III
IV
V
VI
VII
IV | INSPECTION SYSTEM
Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing31
• Visual sensors(IoT) are deployed to monitor defects
• They generate a lot of data and it is difficult to manage large volumes
of data
• A system to handle and make sense out of such large volumes of data
is necessary
• Convolutional Neural Networks can be used for defect classification
• Besides defect type, the degree of defect can also be quantified
IV
I
II
III
IV
V
VI
VII
IV | DEFECT DETECTION
Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing32
L Li et al, Deep Learning for Smart Industry: Efficient Manufacture Inspection System With Fog Computing, IEEE Transactions on Industrial Informatics, 14 (10), October 2018
IV
I
II
III
IV
V
VI
VII
IV | VIDEO ANALYTICS FOR INDUSTRY 4.0 : DRONE AND SAFETY
Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing33
● Health, Safety and Environment (HSE) inspection
● "Bird eye" view
● Camera to capture images, evidences
Drone@ Construction site
● Grid inspection
● Camera to capture any potential issues
● Remote inspection for worker safety
Drone@ grid inspection
Image source: https://bit.ly/2RgKxeL https://bit.ly/2zKXN4N
IV
Predictive Maintenance
Section V
34
I
II
III
IV
V
VI
VII
V | INTELLIGENT PREDICTIVE MAINTENANCE FOR FAULT DIAGNOSIS
Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing35
ML/DL
Algorithms
used for Fault
Diagnosis
How AI Affects the Future Predictive Maintenance: A Primer of Deep Learning
Li et al, ML algorithms used: SVM, Decision Trees, ANNs, Self-Organizing-Maps and other Statistical Machine Learning techniques
V
I
II
III
IV
V
VI
VII
V | PREDICTIVE MAINTENANCE BASED ON DEEP LEARNING
Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing36
Wang and Wang, How AI Affects the Future Predictive Maintenance: A Primer of Deep Learning, 2018
V
Prognostics: probabilities
that the system can fail in
different time horizon/
Maintenance decision.
NLP and Conversational AI
Section VI
37
I
II
III
IV
V
VI
VII
VI | CHATBOT AND SMART MANUFACTURING
Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing38
Image source: : https://bit.ly/2zLZ9Mo
Chatbot features
● Easy to use
● Real-time interactions with devices
● Questions- answer structure
● Natural communication
● Continuous improvement over time
● Personalized relation with engineers (context,
history)
● Helping maintenance crews to verify
factory's condition
○ Field operation – "What is the
temperature reading of a motor #1
of floor #3?"
● Feedback from users on trial runs
○ Improved customer-manufacturer
relationship
● Scalable
VI
I
II
III
IV
V
VI
VII
VI | TAKEAWAY
• Manufacturing is a data rich environment. More automation and new
manufacturing add to the growth of data
• Different area of AI provide ability to improve decision making from
different types of data, and for different applications
• AI is at the center of the future differentiation and progress in
manufacturing
Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing39
VI
THANK YOU!
neXt LIVE with Dr. Ramy Harik
For more information email harik@cec.sc.edu
Slide layout by Alex Brasington

Weitere ähnliche Inhalte

Was ist angesagt?

Was ist angesagt? (20)

Industry 4.0
Industry 4.0Industry 4.0
Industry 4.0
 
Industry 4.0 Implementation, Challenges And Opportunities Of Industry 4.0 : C...
Industry 4.0 Implementation, Challenges And Opportunities Of Industry 4.0 : C...Industry 4.0 Implementation, Challenges And Opportunities Of Industry 4.0 : C...
Industry 4.0 Implementation, Challenges And Opportunities Of Industry 4.0 : C...
 
Smart manufacturing
Smart manufacturingSmart manufacturing
Smart manufacturing
 
Industry 4.0
Industry 4.0Industry 4.0
Industry 4.0
 
Introduction to Industrie 4.0
Introduction to Industrie 4.0Introduction to Industrie 4.0
Introduction to Industrie 4.0
 
Artificial intelligence in industry
Artificial intelligence in industryArtificial intelligence in industry
Artificial intelligence in industry
 
Industry 4.0
Industry 4.0Industry 4.0
Industry 4.0
 
Industry 4 presentation
Industry 4 presentationIndustry 4 presentation
Industry 4 presentation
 
Industry 4.0
Industry 4.0Industry 4.0
Industry 4.0
 
Industry 4.0 PPT PDF for Smart Manufacturing using IIoT (Industrial IoT i.e. ...
Industry 4.0 PPT PDF for Smart Manufacturing using IIoT (Industrial IoT i.e. ...Industry 4.0 PPT PDF for Smart Manufacturing using IIoT (Industrial IoT i.e. ...
Industry 4.0 PPT PDF for Smart Manufacturing using IIoT (Industrial IoT i.e. ...
 
COMPONENTS OF INDUSTRY 4.0
COMPONENTS OF INDUSTRY 4.0COMPONENTS OF INDUSTRY 4.0
COMPONENTS OF INDUSTRY 4.0
 
What is industry 4.0
What is industry 4.0 What is industry 4.0
What is industry 4.0
 
INDUSTRY 4.O
INDUSTRY 4.OINDUSTRY 4.O
INDUSTRY 4.O
 
Industry 4.0: Smart robots for smart factories
Industry 4.0: Smart robots for smart factoriesIndustry 4.0: Smart robots for smart factories
Industry 4.0: Smart robots for smart factories
 
Industry 4.0
Industry 4.0Industry 4.0
Industry 4.0
 
Industry 4.0
Industry 4.0 Industry 4.0
Industry 4.0
 
Smart manufacturing
Smart manufacturingSmart manufacturing
Smart manufacturing
 
Industrial Internet of Things (IIOT)
Industrial Internet of Things (IIOT)Industrial Internet of Things (IIOT)
Industrial Internet of Things (IIOT)
 
Industry 4.0 – the German vision for advanced manufacturing
Industry 4.0 – the German vision for advanced manufacturing  Industry 4.0 – the German vision for advanced manufacturing
Industry 4.0 – the German vision for advanced manufacturing
 
Industry 4.0
Industry 4.0Industry 4.0
Industry 4.0
 

Ähnlich wie Artificial Intelligence in Manufacturing

IIoT Framework for SME level Injection Molding Industry in the Context of Ind...
IIoT Framework for SME level Injection Molding Industry in the Context of Ind...IIoT Framework for SME level Injection Molding Industry in the Context of Ind...
IIoT Framework for SME level Injection Molding Industry in the Context of Ind...
Dr. Amarjeet Singh
 
Cyber Physical Systems Bridging the Digital and Physical Realms for a Smarter...
Cyber Physical Systems Bridging the Digital and Physical Realms for a Smarter...Cyber Physical Systems Bridging the Digital and Physical Realms for a Smarter...
Cyber Physical Systems Bridging the Digital and Physical Realms for a Smarter...
ijtsrd
 
Explainable AI Over the Internet of Things (IoT)_ Overview, State-Of-the-Art ...
Explainable AI Over the Internet of Things (IoT)_ Overview, State-Of-the-Art ...Explainable AI Over the Internet of Things (IoT)_ Overview, State-Of-the-Art ...
Explainable AI Over the Internet of Things (IoT)_ Overview, State-Of-the-Art ...
MurindanyiSudi1
 
Applications of IoT in Manufacturing
Applications of IoT in ManufacturingApplications of IoT in Manufacturing
Applications of IoT in Manufacturing
ijtsrd
 

Ähnlich wie Artificial Intelligence in Manufacturing (20)

Sgd emerging -manufacturing-12-oct 2018
Sgd emerging -manufacturing-12-oct 2018 Sgd emerging -manufacturing-12-oct 2018
Sgd emerging -manufacturing-12-oct 2018
 
IOT in Bangladesh
IOT in BangladeshIOT in Bangladesh
IOT in Bangladesh
 
Pete Wassell (Augmate): AR Smart Glasses and the Industrial IoT
Pete Wassell (Augmate): AR Smart Glasses and the Industrial IoTPete Wassell (Augmate): AR Smart Glasses and the Industrial IoT
Pete Wassell (Augmate): AR Smart Glasses and the Industrial IoT
 
IIoT Framework for SME level Injection Molding Industry in the Context of Ind...
IIoT Framework for SME level Injection Molding Industry in the Context of Ind...IIoT Framework for SME level Injection Molding Industry in the Context of Ind...
IIoT Framework for SME level Injection Molding Industry in the Context of Ind...
 
AI in IoT: Use Cases and Challenges
AI in IoT: Use Cases and ChallengesAI in IoT: Use Cases and Challenges
AI in IoT: Use Cases and Challenges
 
AR Smart Glasses and the Industrial IoT
AR Smart Glasses and the Industrial IoTAR Smart Glasses and the Industrial IoT
AR Smart Glasses and the Industrial IoT
 
Cyber Physical Systems Bridging the Digital and Physical Realms for a Smarter...
Cyber Physical Systems Bridging the Digital and Physical Realms for a Smarter...Cyber Physical Systems Bridging the Digital and Physical Realms for a Smarter...
Cyber Physical Systems Bridging the Digital and Physical Realms for a Smarter...
 
A Platter of Insights on Navigating IoT Trends
A Platter of Insights on Navigating IoT TrendsA Platter of Insights on Navigating IoT Trends
A Platter of Insights on Navigating IoT Trends
 
THE ESSENCE OF INDUSTRY 4.0
THE ESSENCE OF INDUSTRY 4.0THE ESSENCE OF INDUSTRY 4.0
THE ESSENCE OF INDUSTRY 4.0
 
Explainable AI Over the Internet of Things (IoT)_ Overview, State-Of-the-Art ...
Explainable AI Over the Internet of Things (IoT)_ Overview, State-Of-the-Art ...Explainable AI Over the Internet of Things (IoT)_ Overview, State-Of-the-Art ...
Explainable AI Over the Internet of Things (IoT)_ Overview, State-Of-the-Art ...
 
Building Reference Architectures for the Industrial IoT
Building Reference Architectures for the Industrial IoTBuilding Reference Architectures for the Industrial IoT
Building Reference Architectures for the Industrial IoT
 
Security and Privacy Big Challenges in Internet of things
Security and Privacy Big Challenges in Internet of thingsSecurity and Privacy Big Challenges in Internet of things
Security and Privacy Big Challenges in Internet of things
 
Digital Transformation, Industry 4.0 and the Internet of Things: attempt of a...
Digital Transformation, Industry 4.0 and the Internet of Things: attempt of a...Digital Transformation, Industry 4.0 and the Internet of Things: attempt of a...
Digital Transformation, Industry 4.0 and the Internet of Things: attempt of a...
 
lee2015.pdf
lee2015.pdflee2015.pdf
lee2015.pdf
 
Smart Factory Report
Smart Factory ReportSmart Factory Report
Smart Factory Report
 
An Analysis of Benefits and Risks of Artificial Intelligence
An Analysis of Benefits and Risks of Artificial IntelligenceAn Analysis of Benefits and Risks of Artificial Intelligence
An Analysis of Benefits and Risks of Artificial Intelligence
 
Iot tunisia forum 2017 internet of things trends_directions and opportunit...
Iot tunisia forum 2017    internet of things trends_directions and opportunit...Iot tunisia forum 2017    internet of things trends_directions and opportunit...
Iot tunisia forum 2017 internet of things trends_directions and opportunit...
 
Industry 4.0 and Cyber physical systems Intro
Industry 4.0 and Cyber physical systems IntroIndustry 4.0 and Cyber physical systems Intro
Industry 4.0 and Cyber physical systems Intro
 
Applications of IoT in Manufacturing
Applications of IoT in ManufacturingApplications of IoT in Manufacturing
Applications of IoT in Manufacturing
 
Internet of Things Cebu meetup : 1st meetup
Internet of Things Cebu meetup : 1st meetup Internet of Things Cebu meetup : 1st meetup
Internet of Things Cebu meetup : 1st meetup
 

Kürzlich hochgeladen

Kürzlich hochgeladen (20)

Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUnderstanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...
 
🐬 The future of MySQL is Postgres 🐘
🐬  The future of MySQL is Postgres   🐘🐬  The future of MySQL is Postgres   🐘
🐬 The future of MySQL is Postgres 🐘
 
Scaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationScaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organization
 
Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024
 
GenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationGenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day Presentation
 
What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?
 
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot TakeoffStrategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
 
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024
 
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
 
Tech Trends Report 2024 Future Today Institute.pdf
Tech Trends Report 2024 Future Today Institute.pdfTech Trends Report 2024 Future Today Institute.pdf
Tech Trends Report 2024 Future Today Institute.pdf
 
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
 
Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)
 
Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024
 
HTML Injection Attacks: Impact and Mitigation Strategies
HTML Injection Attacks: Impact and Mitigation StrategiesHTML Injection Attacks: Impact and Mitigation Strategies
HTML Injection Attacks: Impact and Mitigation Strategies
 
presentation ICT roal in 21st century education
presentation ICT roal in 21st century educationpresentation ICT roal in 21st century education
presentation ICT roal in 21st century education
 
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, AdobeApidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
 
Exploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone ProcessorsExploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone Processors
 
Strategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherStrategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a Fresher
 

Artificial Intelligence in Manufacturing

  • 1. AI in Manufacturing neXt LIVE with Dr. Amit Sheth
  • 2. I II III IV V VI VII AMIT SHETH, PhD • Founding director of the university-wide Aritificial Intelligence Institute at UofSC (AIISC) • Core research on AI topics such as knowledge infused learning and neuro-symbolic computing, • AIISC has translational research with nearly al of the colleges at UofSC • Fellow of IEEE, AAAI and AAAS Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing2
  • 3. I II III IV V VI VII OUTLINE I. AIISC Introduction II. AI in Manufacturing III. Knowledge Graph/Ontology IV. Computer Vision in Manufacturing V. Predictive Maintenance VI. NLP and Conversational AI VII. Applications of AI in Manufacturing Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing3
  • 5. I II III IV V VI VII I | AIISC DRIVERS AND DISTINCTIONS • To be recognized as the top institution in interdisciplinary AI, AI applications and impact in Southeast US, and among the top in its chosen of selected AI subareas ● Exceptional Student Outcomes ○ Education: 20+ courses in AI ● High impact from translational research ● Apply AI and realize impact across the university and state ● High engagement with communities and industry Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing5 I
  • 6. I II III IV V VI VII I | UNIVERSITY-WIDE MANDATE ● College of Medicine (5) ● College of Nursing (2) ● College of Arts & Science (2) ○ Hazard & Vulnerability Res Inst ○ Institute of Mind and Brain ● College of Pharmacy ○ Colorectal Cancer ○ Digestive Inflammation Index ● College of Information & Communication ● College of Engineering & Computing ○ Civil and Environmental ○ Mechanical & Aerospace ○ Computer Sc & Engg ● College Education ○ ALL4SC ● College of Public Health Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing6 Practically all our work involves real world challenges, real-world data, interdisciplinary collaborators, path-breaking research and innovations, real-world deployments, real world use, and measurable real world impact. I
  • 8. I II III IV V VI VII II | BIG CHANGES IN MANUFACTURING NEED AI ● Automation supported by myriad of technologies including Robots; IoT, Digital Twins ● Strategic changes in Supply Chain - massive disruptions, hiccups in globalization ● Sustainability - traceability and accountability Result: Data Tsunami -> Analytics [CAGR of 30.9% over the forecast period, 2020- 2025: ResearchAndMarkets.com] Possible Solution: AI can help (Recommendation/Planning/Decision Making) [AI in manufacturing is expected to grow at a CAGR of 57.2% during 2020 and 2027: MarketsAndMarkets.com] Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing8 II
  • 9. I II III IV V VI VII II | BIG CHANGES IN MANUFACTURING NEED AI Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing9 “Industry 4.0 is the information-intensive transformation of manufacturing (and related industries) in a connected environment of big data, people, processes, services, systems and IoT-enabled industrial assets with the generation, leverage and utilization of actionable data and information as a way and means to realize smart industry and ecosystems of industrial innovation and collaboration.” From: https://www.i-scoop.eu/industry-4-0/ II
  • 10. I II III IV V VI VII II | BIG CHANGES IN MANUFACTURING NEED AI Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing10 Information is cheap. Understanding is expensive. Karl Fast, Professor of UX Design, Kent State University AI is about converting data into knowledge, insights and actions. II
  • 11. I II III IV V VI VII II | WHAT IS EXPECTED FOR FACTORY OF FUTURE (FOF) Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing11 1. Detect defects throughout the production process. 2. Deploy predictive maintenance to reduce downtime. 3. Respond to real-time changes in demand across the supply chain. 4. Validate whether intricate goods like microchips have been perfectly produced. 5. Reduce costs of small-batch or single-run goods, enabling greater customization. 6. Improve employee satisfaction by shifting mundane tasks to machines. II From: Luke A. Renner, How Can Artificial Intelligence Be Applied in Manufacturing?
  • 12. I II III IV V VI VII II | AI IN MANUFACTURING (WHY? -> BENEFITS) • Direct Automation • 24/7 production • Safety • Low operational cost • Greater efficiency • Quality control • Quick decision making https://www.rowse.co.uk/blog/post/7-manufacturing-ai-benefits Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing12 https://www.industryweek.com/technology-and-iiot/article/22027119/benefits-of- ai-on-manufacturing-a-visual-guide II
  • 13. I II III IV V VI VII II | MANUFACTURING FAILURES: SEVERITY OF THE PROBLEM Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing13 II
  • 14. I II III IV V VI VII II | AI IN MANUFACTURING Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing14 “EVEN THOUGH AI HAS BECOME ONE OF THE HOTTEST TOPICS IN MANUFACTURING TODAY, MOST MANUFACTURERS ARE AT THE START OF THE ADOPTION CURVE. “ THOMAS LEESON “BY THE TIME A LATE ADOPTER HAS DONE ALL THE NECESSARY PREPARATION, EARLIER ADOPTERS WILL HAVE TAKEN CONSIDERABLE MARKET SHARE; THEY’LL BE ABLE TO OPERATE AT SUBSTANTIALLY LOWER COSTS WITH BETTER PERFORMANCE. IN SHORT, THE WINNERS MAY TAKE ALL AND LATE ADOPTERS MAY NEVER CATCH UP.” VIKRAM MAHIDHAR & THOMAS H. DAVENPORT, HBR, DEC 2019 II
  • 15. I II III IV V VI VII II | AI IN MANUFACTURING Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing15 KEY AI SUBAREAS Conversational AI Machine & Deep Learning Natural Language Processing (NLP) Computer Vision Robotics Knowledge Graph (Ontology) II
  • 17. I II III IV V VI VII III | TYPICAL NW ARCHITECTURE FOR FOF: EDGE, FOG, CLOUD Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing17 Figure: Li et al, Online Workload Allocation via Fog-Fog-Cloud Cooperation to Reduce IoT Task Service Delay, 2019 III
  • 18. I II III IV V VI VII II | INDUSTRY NEXT MANUFACTURING @ MCNAIR, UOFSC Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing18 Digital Cell Actual Cell II
  • 19. I II III IV V VI VII III | CONNECTED MANUFACTURING: SMART IOT AS SOLUTION Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing19 III http://wiki.aiisc.ai/index.php/Smart_Data
  • 20. I II III IV V VI VII III | SEMANTICS AT DEVICE AND FACTORY FLOOR NW PROTOCOL LEVELS Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing20 Reference: Gyrard, Amelie, Pankesh Patel, Amit P. Sheth, and Martin Serrano. "Building the web of knowledge with smart iot applications." IEEE Intelligent Systems 31 (5), 2016) P. Desai, A. Sheth, P. Anantharam: Semantic Gateway as a Service Architecture for IoT Interoperability, 2015. ● Moving computation and intelligence closer to data generation. ● Semantic Gateway as a service for interoperability between devices that are using different protocols. III
  • 21. I II III IV V VI VII III | DATA INTEROPERABILITY Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing21 III
  • 22. I II III IV V VI VII III | ANALOGY WITH HUMAN HEALTH Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing22 III
  • 23. I II III IV V VI VII III | TYPES OF INTEROPERABILITY Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing23 Interoperability of ● NWs & protocols ● Data Data interop: ● Domain independent ● Domain specific SenML, SSN Semantic annotation Liu et al, Device-Oriented Automatic Semantic Annotation in IoT, 2017 III
  • 24. I II III IV V VI VII III | ROLE OF ONTOLOGY/KG FOR INTEROPERABILITY: SSN Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing24 Semantic annotation/ labeling help with shared meaning/uniform interpretation of data SSN ontology provides framework for semantic annotation of sensor/device data; Similarly application/ domain specific ontology/knowledge graph can support semantic annotation wrt to the application/domain/task III
  • 25. I II III IV V VI VII III | DIKW: DATA, ANNOTATION, ABSTRACTION, ACTION Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing25 Adapted from: Gyrard, et al, Building the Web of Knowledge with Smart IoT Applications (Extended Version), 2016 ISA 95 model III
  • 26. I II III IV V VI VII III | FACTORY OF FUTURE (FOF) NETWORKING Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing26 Intizar Ali, Pankesh Patel, John Breslin, “Middleware for Real-Time Event Detection and Predictive Analytics in Smart Manufacturing”, 15th International Conference on Distributed Computing in Sensor Systems (DCOSS), 2019. III
  • 27. I II III IV V VI VII III | USE OF KNOWLEDGE GRAPHS IN SMART MANUFACTURING Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing27 VISUAL SENSORS Security Cameras, Drones, Inspection Cameras PHYSICAL SENSORS INDUSTRIAL SENSORS Load cell, Accelerometer, Optical sensor, Potentiometer, RTD temperature sensor HEAT MAP SENSOR Infra-Red heat map sensor DIGITAL TWIN Factory Configuration Process simulators Loops Manufacturing Process Manufacturing Knowledge Representation MANUFACTURING ONTOLOGY MANUFACTURING KG Downstream Tasks ADAPTIVE KG UPDATE MODULE Calculating Ont. + KG update MANUFACTURING SCENE/ EVENT UNDERSTANDING FAULT DETECTION Events Features of Interests Computer Vision + Signal Processing Module KG facts extraction and infusion Enhanced Fault Detection Feedback III
  • 28. I II III IV V VI VII III | REVISITING ARCHITECTURE: DATA TO ABSTRACTION Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing28 III
  • 29. Computer Vision in Manufacturing Section IV 29
  • 30. I II III IV V VI VII IV | COMPUTER VISION EXAMPLES IN FOF • Predictive maintenance of machinery: Using IoT sensors to monitor the production line in real-time to reduce unscheduled downtime and increase productivity • Inspection of defectives: Monitor the assembly lines and identify the defective components • Accurate assembly of components: Alert system for misassembly or mid- operation failure. • Quality control for products: Eg: Acquire Automation implements machine vision that permits manufacturers to inspect bottles in a complete 360- degree view to verify that products are placed in the correct packaging • Health and safety: Deep learning-based AI to track the movement of people and predict where the machines are going to be to avoid dangerous interactions Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing30 IV
  • 31. I II III IV V VI VII IV | INSPECTION SYSTEM Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing31 • Visual sensors(IoT) are deployed to monitor defects • They generate a lot of data and it is difficult to manage large volumes of data • A system to handle and make sense out of such large volumes of data is necessary • Convolutional Neural Networks can be used for defect classification • Besides defect type, the degree of defect can also be quantified IV
  • 32. I II III IV V VI VII IV | DEFECT DETECTION Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing32 L Li et al, Deep Learning for Smart Industry: Efficient Manufacture Inspection System With Fog Computing, IEEE Transactions on Industrial Informatics, 14 (10), October 2018 IV
  • 33. I II III IV V VI VII IV | VIDEO ANALYTICS FOR INDUSTRY 4.0 : DRONE AND SAFETY Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing33 ● Health, Safety and Environment (HSE) inspection ● "Bird eye" view ● Camera to capture images, evidences Drone@ Construction site ● Grid inspection ● Camera to capture any potential issues ● Remote inspection for worker safety Drone@ grid inspection Image source: https://bit.ly/2RgKxeL https://bit.ly/2zKXN4N IV
  • 35. I II III IV V VI VII V | INTELLIGENT PREDICTIVE MAINTENANCE FOR FAULT DIAGNOSIS Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing35 ML/DL Algorithms used for Fault Diagnosis How AI Affects the Future Predictive Maintenance: A Primer of Deep Learning Li et al, ML algorithms used: SVM, Decision Trees, ANNs, Self-Organizing-Maps and other Statistical Machine Learning techniques V
  • 36. I II III IV V VI VII V | PREDICTIVE MAINTENANCE BASED ON DEEP LEARNING Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing36 Wang and Wang, How AI Affects the Future Predictive Maintenance: A Primer of Deep Learning, 2018 V Prognostics: probabilities that the system can fail in different time horizon/ Maintenance decision.
  • 37. NLP and Conversational AI Section VI 37
  • 38. I II III IV V VI VII VI | CHATBOT AND SMART MANUFACTURING Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing38 Image source: : https://bit.ly/2zLZ9Mo Chatbot features ● Easy to use ● Real-time interactions with devices ● Questions- answer structure ● Natural communication ● Continuous improvement over time ● Personalized relation with engineers (context, history) ● Helping maintenance crews to verify factory's condition ○ Field operation – "What is the temperature reading of a motor #1 of floor #3?" ● Feedback from users on trial runs ○ Improved customer-manufacturer relationship ● Scalable VI
  • 39. I II III IV V VI VII VI | TAKEAWAY • Manufacturing is a data rich environment. More automation and new manufacturing add to the growth of data • Different area of AI provide ability to improve decision making from different types of data, and for different applications • AI is at the center of the future differentiation and progress in manufacturing Dr Harik's neXt LIVE with Dr. Amit Sheth on AI in Manufacturing39 VI
  • 40. THANK YOU! neXt LIVE with Dr. Ramy Harik For more information email harik@cec.sc.edu Slide layout by Alex Brasington