View
8
Download
3
Category
Preview:
Citation preview
PUBLIC
Dr.-Ing. Achim Krüger, Vice President, Line of Business Asset Management, SAP SE
July 12, 2017
SAP Enterprise Asset ManagementSolution Overview and Strategy in a Nutshell
2© 2017 SAP Leonardo Live. All rights reserved. I PUBLIC
The information in this presentation is confidential and proprietary to SAP and may not be disclosed without the permission
of SAP. This presentation is not subject to your license agreement or any other service or subscription agreement with SAP.
SAP has no obligation to pursue any course of business outlined in this document or any related presentation, or to develop
or release any functionality mentioned therein. This document, or any related presentation and SAP's strategy and possible
future developments, products and or platforms directions and functionality are all subject to change and may be changed
by SAP at any time for any reason without notice. The information in this document is not a commitment, promise or legal
obligation to deliver any material, code or functionality. This document is provided without a warranty of any kind, either
express or implied, including but not limited to, the implied warranties of merchantability, fitness for a particular purpose, or
non-infringement. This document is for informational purposes and may not be incorporated into a contract. SAP assumes
no responsibility for errors or omissions in this document, except if such damages were caused by SAP´s willful misconduct
or gross negligence.
All forward-looking statements are subject to various risks and uncertainties that could cause actual results to differ
materially from expectations. Readers are cautioned not to place undue reliance on these forward-looking statements, which
speak only as of their dates, and they should not be relied upon in making purchasing decisions.
Legal disclaimer
3© 2017 SAP Leonardo Live. All rights reserved. I PUBLIC
Technology
enablers
Business
challenges
SAP Enterprise Asset Management (SAP EAM) solutionTrends in asset management
Internet of Things (IoT)
to scale connectivity
Big Data for getting
insight from IT and OT
Analytics for prediction
and simulation
Machine learning
to improve
business decisions
Enterprise mobility
to empower employees
Cloud for collaboration
ISO 55001, ISO 14001,
ISO 45001, and the like
Optimizing cost, risk,
and performance
Balancing OPEX with
CAPEX
Meeting stakeholder
expectations
Empowering
practitioners
Facilitating
collaboration among
EPCs, OEMs,
service providers,
and operators
4© 2017 SAP Leonardo Live. All rights reserved. I PUBLIC
Connecting all stakeholders
alongside the asset lifecycle
Connecting corporate objectives
with the asset system
SAP Enterprise Asset ManagementAsset management in an ever-more-connected world
Business needs
analysisPlan and design
Acquisition and
commission
Operation and
maintenance
Configuration and
change management
Decommission
and disposalAsset
Cost
RiskPerformance
Manufacturer
Supplier
EPC
Service provider
Owner or operator
Dealer
IT OTConnecting IT with OT
55001
www.sap.com/eam
5© 2017 SAP Leonardo Live. All rights reserved. I PUBLIC
SAP Enterprise Asset ManagementSupporting asset management processes from end to end
Portfolio and project
management
Portfolio
management
Project connectivity
Project
management
Resource management
Idea management
Asset operations
and maintenance
Maintenance planning and
scheduling
Maintenance
execution
Mobile asset
management
Asset strategy
and performance
Environment, health,
and safety
Health and safety
management
Maintenance safety
and permit to work
Environment
management
Management
of change
Incident management
Asset
network
Asset information
governance
Predictive maintenance
and service
Asset information
collaboration
6© 2017 SAP Leonardo Live. All rights reserved. I PUBLIC
Systems of
record
Bimodal IT according to GartnerSystems of record versus systems of innovation
Source: Gartner
Systems of
innovation
Systems of
differentiation
Mode 1
Mode 2
Go
ve
rna
nc
e
+
–
Ch
an
ge
+
–
SAP Integrated
Business
Planning
SAP Leonardo
7© 2017 SAP Leonardo Live. All rights reserved. I PUBLIC
Envisioned logical architecture for SAP Enterprise Asset ManagementStrategic direction
Business intelligence
Mode 1 Mode 2
Data foundation
SAP Ariba
solutions
SAP SuccessFactors
solutions
SAP Fieldglass
solutions
SAP Digital Boardroom
Differentiate Business
Machines Sensors OT Systems Edge
Intelligently
connect people,
things, and
businesses
Differentiate
businessesHyperautomate business
processes
Run businesses
Deliver insights to drive
strategic decisions
Steer businesses
Embrace data
Orchestrate data of any
volume, velocity, and variety
Asset
Intelligence
Network
Predictive
Maintenance
SAP Asset Strategy
and Performance
Management
Mobile…
STO
Internet of Things
SAP Leonardo
IoT Foundation
Master data
EH&SPM
FI
CO
MM PLM …
PS MRS
SAP Asset
Intelligence
Network
SAP Predictive
Maintenance and
Service
Mobile
Digital core
SAP Integrated
Business Planning
SAP Leonardo
8© 2017 SAP Leonardo Live. All rights reserved. I PUBLIC
SAP Predictive Maintenance and Service From sensor to insight to outcome
IT/OT
convergence
Big Data ingestion
Big Data
infrastructure
Merging sensor data
with business
information
Maintenance
activities
Prioritized
maintenance and
service activities
Optimized warranty
and spare parts
management
Prescriptive
maintenance
Quality improvements
Data
analysis
Root cause analysis
Asset health
monitoring
Machine learning
Anomaly detection
Triggering of
corrective actions
Connected
assets
Onboarding
Connectivity
Device
management
Security
Business
value
Customer experience
Increased quality
Lower costs
Operational efficiency
R&D effectiveness
Material procurement
Sensor Data Insight Action Outcome
9© 2017 SAP Leonardo Live. All rights reserved. I PUBLIC
SAP Predictive Maintenance and ServiceHow can information systems help?
Connected
assets and sensors
OT
systems
(such as SCADA)
Other
data sources
(such as weather)
Digital core
(SAP S/4HANA)
SAP Leonardo IoT
capabilities
Engineering
rules
Life
indicators
Distance
scoring
Anomaly
detection…
Agile planningRemote monitoring Alerts and actions
10© 2017 SAP Leonardo Live. All rights reserved. I PUBLIC
Availability through the cloud or on
premise
Flexible extension concept to
build industry- or customer-specific
models and analytics
Scalable machine learning engine
that drives data science insights
into our business processes
Flexible visualizations across
equipment structures
Comprehensive process
integration: alert, discover,
remedy
SAP Predictive Maintenance and ServiceSolution components and value drivers
Business dataMachine data
SAP Leonardo Foundation
SAP Leonardo for Edge Computing
Business user
Domain expert
Data scientist
Data managerSAP Leonardo IoT Foundation
SAP Leonardo IoT Edge
Machine learning engine
Insight provider catalog
SAP Predictive Maintenance and Service
Asset health
control center
Asset health fact
sheet
Logistics and maintenance
execution systemsActions
Insights
Alerts
Raw
data
11© 2017 SAP Leonardo Live. All rights reserved. I PUBLIC
Condition data allows for
a ranking of assets
according to a health score.
For “healthier” assets,
the service interval
can be prolonged, while it can be
shortened for others.
This results in fewer failures
and lower maintenance costs.
SAP Asset Strategy and Performance Management Adding more efficiency by looking at the fleet
Preventive
(static)
Run-to-failure
Preventive
(static)
Preventive
(agile)
Run-to-failure
Cost
12© 2017 SAP Leonardo Live. All rights reserved. I PUBLIC
Benefits
Increase overall asset availability
Increase MTBF – increase equipment reliability
Improve utilization of assets
Control maintenance spend
Reduce work backlog
Identify savings opportunities through preventive and
predictive maintenance
Reduce capital tied up in spare parts inventory
Adopt a proactive and targeted maintenance strategy
Change the sequence of the process using point apps
Solution integration points
SAP Asset Intelligence Network
SAP Predictive Maintenance and Service
SAP ERP application or SAP S/4HANA (PM, MM, FI/CO,
PP functionalities)
SAP Integrated Business Planning
SAP Asset Strategy and Performance Management (planned)End-to-end process enablement
Process innovation
Classification of assets
into groups
Asset criticality and risk assessment
Collaborative failure
modes libraryPerform FMEA
Analyze systems and
functionsPerform RCM
Analyze and optimize
maintenance strategy
CAPEX / OPEX inputs
to maintenance
strategy
Bad actor
management and
spares optimization
Integrations and
extension points to 3rd-
party systems
Perform RCA, ETA
Project manager
review
This is the current state of planning and may be changed by SAP at any time.
MTBF – mean time between failures; FMEA – failure mode and effects analysis; RCM – reliability-centered maintenance; RCA – root cause analysis
13© 2017 SAP Leonardo Live. All rights reserved. I PUBLIC
What does digital transformation mean for enterprise asset management?
Connect to the asset
Bring together information from operational and business systems (IT/OT convergence)
Utilize the IoT for scaling transparency without neglecting existing information sources
Predict asset system behavior
Avoid unplanned downtime and major operational consequences through simulation and prediction
Discover patterns of failure and preserve operational integrity
Blend business IT information with operational (OT) data
Share asset information and collaborate
Activate the ecosystem of OEMs, EPCs, service providers, and operators
Make sure there is one version of truth on asset master data
Use a business network to enable integrated processes in the cloud
Digital transformation in asset management driven by IoT, cloud, and
business networks
14© 2017 SAP Leonardo Live. All rights reserved. I PUBLIC
SAP solutions for the asset management line of businessWhere to find more information about our road map and innovation
Road maps: Value maps:
http://www.sap.com/roadmaps http://www.sap.com/solutionexplorer
Innovation discovery:
http://sapsupport.info/support-innovations/innovation-discovery/
Dr. Achim Krüger
Vice President, Line of Business Asset Management
SAP SE
Dietmar-Hopp-Allee 16
69190 Walldorf, Germany
T +49 6227 7-60975
F +49 6227 78-38446
M +49 160 3603569
S +49 6227 7-49510
achim.krueger@sap.com
Thank you.
More information:
www.sap.com/eam
www.sap.com/roadmaps
www.sap.com/solutionexplorer
http://scn.sap.com/community/eam
No part of this publication may be reproduced or transmitted in any form or for any purpose without the express permission of SAP SE or an SAP affiliate company.
The information contained herein may be changed without prior notice. Some software products marketed by SAP SE and its distributors contain proprietary software components
of other software vendors. National product specifications may vary.
These materials are provided by SAP SE or an SAP affiliate company for informational purposes only, without representation or warranty of any kind, and SAP or its affiliated
companies shall not be liable for errors or omissions with respect to the materials. The only warranties for SAP or SAP affiliate company products and services are those that are
set forth in the express warranty statements accompanying such products and services, if any. Nothing herein should be construed as constituting an additional warranty.
In particular, SAP SE or its affiliated companies have no obligation to pursue any course of business outlined in this document or any related presentation, or to develop or release
any functionality mentioned therein. This document, or any related presentation, and SAP SE’s or its affiliated companies’ strategy and possible future developments, products,
and/or platform directions and functionality are all subject to change and may be changed by SAP SE or its affiliated companies at any time for any reason without notice. The
information in this document is not a commitment, promise, or legal obligation to deliver any material, code, or functionality. All forward-looking statements are subject to various
risks and uncertainties that could cause actual results to differ materially from expectations. Readers are cautioned not to place undue reliance on these forward-looking statements,
and they should not be relied upon in making purchasing decisions.
SAP and other SAP products and services mentioned herein as well as their respective logos are trademarks or registered trademarks of SAP SE (or an SAP affiliate company)
in Germany and other countries. All other product and service names mentioned are the trademarks of their respective companies.
See http://global.sap.com/corporate-en/legal/copyright/index.epx for additional trademark information and notices.
© 2017 SAP SE or an SAP affiliate company. All rights reserved.
Building the Smart
Railroad
SAP Leonardo Live event
Jeroen De Roeck
10.176 Main Signals(31/12/2016)
5.905 km Overhead lines(31/12/2016)
6.511 km of Main Track(31/12/2016)
11.769 Civil Engineering Constructions (31/12/2016)
7000+ Employees(31/12/2016)
1.751 Level Crossings (31/12/2016)
THE BELGIAN RAIL INFRA MANAGER
Key Figures Asset Management
SAP objects>500.000 Functional locations>2.000.000 Pieces of equipment
Spare Parts 270 M€
“STUPID Assets” “SMART Assets”
NOT CONNECTED CONNECTED
19July 2017 Infrabel – Building the Smart Railroad
Sensors &
Intranet of Things
Sensors &
Measure Trains
“STUPID Assets” “SMART Assets”
NOT CONNECTED CONNECTED
20July 2017 Infrabel – Building the Smart Railroad
Preventive
maintenance
plans
ASSET
DATA
Incidents
Preventive/Condition/Predictive-based
maintenance SAP
Technicians
& TABLETS
PLANNER
Digital Strategy
21July 2017 Infrabel – Building the Smart Railroad
Infrabel Movie
22July 2017 Infrabel – Building the Smart Railroad
0,8
1
1,2
1,4
1,6
1,8
2
0,02 0,2
0,38
0,56
0,74
0,92
1,1
1,28
1,46
1,64
1,82 2
2,18
2,36
2,54
2,72
2,9
3,08
3,26
3,44
3,62
3,8
3,98
4,16
4,34
4,52
4,7
4,88
5,06
5,24
5,42
5,6
5,78
5,96
01/11/15 01:58:17.920
01/11/15 02:12:07.940
03/11/15 11:07:33.920
04/11/15 05:08:32.920
04/11/15 06:46:44.920
06/11/15 10:10:20.920
07/11/15 13:08:19.940
09/11/15 08:08:56.940
09/11/15 08:12:10.920
09/11/15 08:14:42.920
09/11/15 09:51:52.940
average
EBP
EBP logbook
PQube
Current Curves (1.000.000)
100 Turnouts
Turnout – motor
SAP Enterprise Asset
Management (SAP EAM)
First steps in IOT – the PQUBE case
23July 2017 Infrabel – Building the Smart Railroad
• Turnouts are more or less a blackboxInformation currently available from distance
• Left or right
• In/out control
• Placing the Pqube sensor should increase the• Visibility on the functioning of a turnout
• Provide Data to examine behaviour 0,8
1
1,2
1,4
1,6
1,8
2
0,02 0,2
0,38
0,56
0,74
0,92
1,1
1,28
1,46
1,64
1,82 2
2,18
2,36
2,54
2,72
2,9
3,08
3,26
3,44
3,62
3,8
3,98
4,16
4,34
4,52
4,7
4,88
5,06
5,24
5,42
5,6
5,78
5,96
01/11/15 01:58:17.920
01/11/15 02:12:07.940
03/11/15 11:07:33.920
04/11/15 05:08:32.920
04/11/15 06:46:44.920
06/11/15 10:10:20.920
07/11/15 13:08:19.940
09/11/15 08:08:56.940
09/11/15 08:12:10.920
09/11/15 08:14:42.920
09/11/15 09:51:52.940
average
First steps in IOT – Goals with Pqube project
24July 2017 Infrabel – Building the Smart Railroad
Going from individual measurements to current curves
• Plot measurement values in time
• Business value:
Current curves
A correct image of the physical functioning of a turnout
Data analytics – from measurement to data
25July 2017 Infrabel – Building the Smart Railroad
• Each turnout has it own curve that evolves during time
• Each type of turnout has a typical curve
• It defines the ‘DNA’ of the turnout
Data analytics – What we learned
26July 2017 Infrabel – Building the Smart Railroad
Determine algorithms to define ‘normal’ behaviour
Each unique turnout has it own characteristic evolution of the curve
Curve:
• Difference for left or right movements
• Variation in current due to changes in mechanical properties
0
1
2
3
4
5
6
7
8
9
1 10 19 28 37 46 55 64 73 82 91 100
109
118
127
136
145
154
163
172
181
190
199
208
217
226
235
244
253
262
271
280
289
298
24/03/15 10:53:34.920
average
Data analytics – Define Models
27July 2017 Infrabel – Building the Smart Railroad
Determine algorithms to define ‘abnormal’ behaviour• Abnormal current consumption
• Longer runtimes
• Larger deviations = malfunction
• Specific patterns ie. Bad alignment worm wheel
Data analytics – Define Models
28July 2017 Infrabel – Building the Smart Railroad
Normalisation
• Flatten out differences in timestamp between different systems
• Only keep reliable measurements
0
1
2
3
4
5
6
7
8
1 14 27 40 53 66 79 92 105
118
131
144
157
170
183
196
209
222
235
248
261
274
287
300
21U R 01/01/15 10:19:22.920
21U R 01/01/15 12:49:56.940
21U R 01/01/15 14:49:15.940
21U R 01/01/15 18:48:53.940
21U R 02/01/15 07:48:17.920
0
1
2
3
4
5
6
7
8
1 35 69 103 137 171 205 239 273 307 341 375 409 443 477 511 545 579 613 647 681 715 749 783 817 851 885 919 953 987 1021
L2 Amp (A)
L2 Amp (A)
L2 Amp (A)
L3 Amp (A)
L3 Amp (A)
L2 Amp (A)
L2 Amp (A)
L1 Amp (A)
L3 Amp (A)
L2 Amp (A)
Data analytics – Define Models
29July 2017 Infrabel – Building the Smart Railroad
Building a predictive model
• Each movement gets a calculated number
Number Anomaly Category
0.9762 normal
7.84222 failing F26
0.96101 normal
12.7684 failed f30
12.5305 failed f30
12.4308 failed f40
11.8506 failing f30
10.0133 failing f30
6.42567 failing f30
0.71324 normal
6.07957 failing f26
0.71649 normal
0.74115 normal
Data analytics – Define Models
30July 2017 Infrabel – Building the Smart Railroad
• Normal curve = 1
• Early warning> 1,4
• Includes false positives
• Warning >= 2
• No false positives
• Failing >= 3,8
• Failed >= 11,9
Data analytics – Define Models
Building a predictive model
• Each movement gets a calculated number
31July 2017 Infrabel – Building the Smart Railroad
Data analytics – Introduce AI technology
32July 2017 Infrabel – Building the Smart Railroad
Unsupervised learning
Dimensionality reduction using neural networks
Data analytics – Introduce AI technology
Normal data
Over Current
Not locking
33July 2017 Infrabel – Building the Smart Railroad
• Increase installed base: install Pqube on critical turnouts.
• Avoid unnecessary activity in the field
• Better planning and preparation based on indications
from predictive model
• Reduction of unplanned downtime by early warning
• Number of false positives to be managed
• Prevent extended maintenance downtime due to
unforeseen activities
Pqube Project – Business value
Reduce cost of
operations
Reduce
unplanned
downtime
34July 2017 Infrabel – Building the Smart Railroad
Pqube Project – Leverage IoT Business value
Cost
Risk
Starting from traditional Preventive Maintenance Strategy
• Low Risk
• High Cost
• Adapt preventive Maintenance strategy
• Cost of visits
• Risk
• Use Predictive model to lower the Risk
• Total cost of Predictive Model + Lower Maintenance
strategy < Traditional Preventive Maintenance
• New balance between cost and risk
35July 2017 Infrabel – Building the Smart Railroad
2017 2018
Turnout
Measurement system
Turnout
Video Inspection system
TVS
Track
Video System
DB 500 Gb/year
Video 100 Tb/year
SGS
Switch
Geometry System
100 Tb/year
Next steps in making assets ‘smart’
Increasing the business valueLin
ear
assets
Sin
gu
lar
Assets
36July 2017 Infrabel – Building the Smart Railroad
First steps in IoT – What we learned
Pqube case enabled us to:
• Learn and understand possibilities of IoT @ Infrabel
• In the beginning: a lot of manual work involved
• Unsupervised learning had the same result much faster
• Looking for additional IoT opportunities:
• Monitoring Control Unit
• Enhance ‘old’ equipment with nonintrusive new technology
37July 2017 Infrabel – Building the Smart Railroad
July 2017
Next steps in IoT – Monitoring Control Unit
38July 2017 Infrabel – Building the Smart Railroad
MCU:
• Remote measurement/monitoring of:
• Batteries
• Current rectifier
• Active alerts
• Configuration parameters managed
remotely
• Business Value:
• Fewer physical visits necessary.
• Visit takes 3,5 hours incl travel * 750 installations = 2625 hours saved
• Active control of parameters, limit human errors
• Early warning on battery issues
Next steps in IoT – Monitoring Control Unit
39July 2017 Infrabel – Building the Smart Railroad
Next steps in IoT – LED’s tele-monitoring in RTF boxes
using Computer Vision
40July 2017 Infrabel – Building the Smart Railroad
State-of-the-art research and development at Infrabel
Next steps in IoT – Asset classification with Computer
Vision
41July 2017 Infrabel – Building the Smart Railroad
Higher
Data
Quality
Quicker
Response
Measurement
database
Reports
Measurement
Data
Incident
Intervention
Malfunction
Asset Master data
Verified measurement results
Predictive notifications
Asset owner (expert) + data scientistTechnician
SAP EAM
Assets checked by
Measurement trains
Assets to be maintained
Asset Management information flow
Model
Live
data
Less
manual
work
42July 2017 Infrabel – Building the Smart Railroad
How to digest all the data
Use of flexible reporting in
SAP Lumira software
• Meaningful insight on
combined data
• KPI models based on
previous data analysis
experience
• Tree maps and
geographical
visualisation to focus on
the important stuff
43July 2017 Infrabel – Building the Smart Railroad
How to digest all the data
SAP EAM with GEOe
support
• Visual way of working
• Quickly identifying
assets that need
maintenance
• Real time follow-up
44July 2017 Infrabel – Building the Smart Railroad
How to digest all the data
SAP EAM and Expert
systems
• Visualising linked assets
• Connecting measurement
information
• Display information on
previous measurements
• All information available
from the back-end system
45July 2017 Infrabel – Building the Smart Railroad
How to digest all the data
Mobile SAPUI5 apps
• Consult measurement
history
• Perform checklists
• Access location-based
observations by
maintenance crews
46July 2017 Infrabel – Building the Smart Railroad
Separate engineering and production system
• Production used to plan and predict
• Engineering to develop predictive models
and rules
Proven models to be displayed in production
system
Only hot data in Production
Warm data in Engineering based on extended
Storage.
POC for future architecture
Engineering System
• Larger time series
Based on:• SAP HANA platform
• SAP IQ software
• Hadoop
• SAP Data Services software
Production System
• Actual time series
Based on:• SAP HANA platform
• SAP IQ software
• Hadoop
• SAP Data Services software
47July 2017 Infrabel – Building the Smart Railroad
Increase step by step the maturity in IOT scenarios
How we proceed: Start Small - Think Big
• Connect and centralize
connected assets
• Make ‘stupid’ assets
‘smart’ with sensors
• Collect data – even if
you don’t use it yet
• Automate the models
with AI
• Interconnect with SAP
EAM for preventive and
corrective actions
• Start working on analytics
and reporting part
• Set up organisations with
data scientists
• Interconnect different
disciplines
• Centralize all data in a Big
Data engineering and
production environment
• Integrate useful data in
mobile apps for field workers
• Work with Geo-enabled
videostreams, photos
• Smart visualisation and
analytics
• Start building models
• Predictive models
• Anomaly detection
• Engineering rules
• Data filtering and alerting
• Build a business confidence
level
48July 2017 Infrabel – Building the Smart Railroad
• Bring in Predictive skills (AI knowledge) to get started
• Check the economic model for placing sensors
• Quality of sensor is crucial: avoid sensor failures
• Huge change on way of working: build confidence level first
• Easy and simple solutions can work.
• Maturity can increase step by step.
49
Key Messages
July 2017 Infrabel – Building the Smart Railroad
Thank you
50July 2017 Infrabel – Building the Smart Railroad
Recommended