8. GET INSIGHTS
Getting near real time
insights is difficult and time
consuming due to
disconnected data across
regions and product
REDUCING COST
Sub-optimal monitoring
capabilities prevent
manufacturers from reducing
the cost of service and
remaining competitive
NEW REVENUE
Uncontrolled costs and risks
make it challenging to secure
support for creating revenue
streams through new
innovative services or
business models
9. Connected chillers are
back online 9x faster
than unconnected
equipment, avoiding
more than $300,000 in
hourly downtime costs
Data from sensors and
systems to create
valuable business
intelligence and reduce
downtime by 50%
Reduced its accident rate
by 25% and fuel usage
by 20%, reporting
annual savings of $1.8
million
Cut down-time cut for
each packaging line by
up to 48 hours, saving
€30,000 for customers
Keeping farmers informed
about irrigation, disease
control diseases, and pest
has led to increased yields
of 30%, and a 20%
reduction in water use
Rolls Royce “power by the
hour” model provides
maximize availability by
cutting fuel consumption
by 1% and up to $250,000
per plane, per year.
Access to production and
supply chain data worldwide,
reduced downtime costs by
as much as $300,000 per day
Licorice extruders on
Twizzler’s production
line are performing at
peak optimization,
saving over
$500K/year on
materials alone
Enabled customers to
transport more than
1M additional tons of
cargo, and reduce fuel
consumption by 17%
10. 微軟工業物聯網策略 – 結合產業龍頭 帶動創新
Enable innovation that matters to the industry on Microsoft and Microsoft partners
Digital Twin
Smart
Manufacturing
Asset
Management
Predictive
Maintenance
Field Services
Quality
Assurance
Others…
Compute, Network, Storage, IoT, Data & AI platform, Security, Open platform
Stability/
Quality
New business
model
Capacity
planning
Minimize
unplanned
downtime
Improve
workplace
safety
Compliance Others…
11.
12. 智慧製造數位轉型各大階段
“Pay-as-you-go”,
Outcome-based
products
Products that never break
“New business models”
Services
7
Digital feedback
loops,
Functions
How can an autonomous response be achieved?
“Self-optimizing”
Adaptability
6
AI Models,
Machine
Learning
What will happen?
“Being prepared”
Predictions
5
Time Series
Insights,
Hierarchical
Data Modeling
Why is it happening?
“Understanding”
Transparency
4
Telemetry
Dashboards
What is happening?
“Seeing”
Visibility
3
Edge Gateways
How to Connect?
“Plugging in”
Connectivity
2
PLCs/IPCs
What Data?
“Defining Tags”
Computerization
1
Value
Time設備聯網 數位化 數據分析可視化 可預測化 自動因應 服務化
13. PREDICTIVE ANALYTICS
I N FACT O RY OF THE FUTU RE
AT JABI L
▪ Improving Quality
– Predict downstream defects products in
upstream processes and evaluate the
impact to production BEFORE they happen
– Advanced statistics for early warning
detection of quality processes going out of
control long before they happen
▪ Equipment Optimization
– Machine learning algorithms used for
autonomous equipment adjustments and
M2M with no operator intervention
▪ Increasing Equipment Uptime
– Avoid unplanned downtime by predicting
future equipment failures
– Optimize maintenance schedules and
reduce costs
14. • Majans uses Zeiss Corona process measurement for failure
detection and quality control, which are mounted in-line and
checking moisture/salt, and there are only 3 such Zeiss Corona
spectrometers in the world. However, the interface to this only
speaks OPC DA.
• IIoT helped ZEISS to connect OPC DA to OPC UA, and also
enabled this at Majans for the real-time streaming of Zeiss
Corona process measurement into Azure IoT Hub. The data
flow ingests 15 PLC tags/measures to IoT Hub using the OPC UA
Publisher, which is running as a native .NET core app on an
Omron Industrial PC (IPC). This way we had nodes available via
OPC UA to synchronize with the OPC DA tags from the ZEISS
OPC Server.
• The measurements may be small (just 5 parameters for salt,
moisture and 3 more for color) but very important to our
customer for establishing quality in their products. Having the
capability to do this real-time is a big achievement for this
industry (versus a QA/QC sampling lab).
Majans – Quality Assurance
18. User experiences
Dashboards Mixed Reality Interactive speech Gestures
Preconfigured Azure IoT Suite and SaaS applications
Remote monitoring Predictive maintenance Connected factory Microsoft IoT Central
Analytics and artificial intelligence
HDInsight Machine
Learning
Data Lake
Analytics
Azure Time
Series Insights
Bot
Framework
Operations
Technology
Enterprise business processes
PLM ERP SCMCRM
Home
IT architecture
EdgeAnalyticsDeviceAgent
StreamAnalytics
onedge
Logic
Apps
API
integration
BizTalk
Services
Azure StackSQL Server
MES & Enterprise IT Business integration
Hot path analytics and application platform
Cold path analytics and storage
Stream Analytics Event Hubs Service Fabric (Actors) Functions
Data Factory DocumentDB SQL Database Data Lake Store
Field Gateway
Cloud Gateway
Azure IoT Gateway
Azure IoT
Hub
(device
provisioning)
Cognitive
Services
L3: Mfg Ops
Mgmt, MES,
CAD, PLM
L2: Supervisory
Control,
SCADA,
HMI
L1: Plant
Control PLC,
DCS, IPC
L0: Physical
Equipment,
I/O, Devices,
Sensors
L4: Business
Planning
21. 從機械雲, 檢測雲到智慧製造
Microsoft’s Infrastructure & Data Platform 開放整合的數據平台
(Open, Common Data Model concept)
新舊機台聯網 Connect your “Things” (Greenfield or Brownfield)
快速部署各場域應用 Onboard/ Off board “Use Cases”
Predictive
Maintenance
預保維修
CAD/CAM
加工模擬管理
CNC
Calibration
機台校正
AI for QA
瑕疵檢測
OEE
產能優化
22. Recognition: Microsoft is recognized as the first to…
Microsoft is a leader in
the Forrester Wave for
IoT Software Platforms
Microsoft is a Leader in
the IDC MarketScape for
IoT platforms across
various use cases
Microsoft is a leader in the
Research Leaderboard
assessment of strategy and
execution for 15 IoT
platform providers
Azure IoT is the only
cloud platform that was
determined as best in
class in every category
• Deliver IoT solution accelerators | SaaS and PaaS for IoT | AA/AI at the edge
• Solve device provisioning at scale | Support OPC UA for manufacturing