SAP Predictive Maintenance and Service · Collaborative asset management bringing key stakeholders...
Transcript of SAP Predictive Maintenance and Service · Collaborative asset management bringing key stakeholders...
2© 2018 SAP SE or an SAP affiliate company. All rights reserved.
Legal disclaimer
▪ 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.
3© 2018 SAP SE or an SAP affiliate company. All rights reserved.
Standalone and isolated assets
Untrusted & disparate asset information
Limited analytical capabilities
Reactive maintenance
Disconnected systems and lifecycle
Selling equipment
Traditional budget based maintenance
planning
Paper-based work instructions
Optimized for physical structure
Connected and smart digital twins
Collaborative single source of truth
Real time analytics with simulation
Prescriptive maintenance
Closed loop product and asset lifecycle
Pay-per-use / Equipment-as-a-Service
Cost / Risk / Performance based maintenance
strategy
Interactive work instructions with 3D visualizations
Mechatronics / Software in products/assets
NowYesterday
Pay per use
Asset Management TrendsTransformation to digital connected assets
Digital Twins and 3D
Visualization
4© 2018 SAP SE or an SAP affiliate company. All rights reserved.
SAP Vision for Asset Management
Collaborative
Scalable
Real Time
Connected
Cloud Platform
BasedDigital Disruption
Adaptable
Real Time Insights
Optimization via
Prediction
Next gen tech ML,
Block chain, 3D printing
Mobile First / Fiori UX
Unified data and processes with
PLM, Manufacturing and Service
Share & Collaborate
natively
Base for Industry
Extensions
Partner ecosystem
Opportunity
ElectronicsSoftware Modular Services
Full Digital Representation of Assets along their Lifecycle delivering an embedded,
collaborative and real-time set of Next Generation Processes and Systems
5© 2018 SAP SE or an SAP affiliate company. All rights reserved.
SAP Leonardo IoT
for Asset Management
Digital Core: System of
Record
Digital Innovation: System of
Innovation
SAP Leonardo IoT for Asset ManagementEnabling intelligent insights
Asset
Strategy &
Performance
Asset
Intelligence
Network
Predictive
Maintenance
& Service
Predictive
Engineering
Insights
S/4HANA
&
ECC
Maintenance
Management
An architecture built for next generation
Enterprise Asset Management
Digital Core
Corrective, emergency and preventive maintenance planning &
execution via notification and order processing in an integrated
system
Digital Innovation
• Asset Central – Provides a re-usable asset registry across IoT
applications for seamless integration and data consistency
• SAP Asset Intelligence Network
Collaborative asset management bringing key stakeholders
(operator, OEM, service providers, …) together in a digital
ecosystem solving complex execution, predictive and planning
activities with centrally managed asset information
• SAP Predictive Maintenance and Service
Enables enhanced predictive maintenance techniques to
optimize EAM business processes for greater asset availability
and reduced cost
• SAP Asset Strategy and Performance Management
Define and plan maintenance execution strategies holistically
(insight/foresight; insights from network) for improved
performance
• SAP Predictive Engineering Insights
Model and visualize the physical structure of an asset for real-
time calculation of stress and fatigue to drive predictions
Integration
Asset
Central
7© 2018 SAP SE or an SAP affiliate company. All rights reserved.
SAP Predictive Maintenance and Service
Preventive
(static)
Run-to-Failure
Preventive
(static)
Predictive/
On-Condition
(agile)
Run-to-Failure
OP
EX
Step 1today Step 2
future
Few Data
Big Data
Few Data
The Internet of Things is leading to
increased use of on-condition and
predictive maintenance strategies
Although still relevant, reactive
and preventive maintenance
strategies do little to guard against
unplanned equipment downtime
and result in high cost
The goal is to
increase our use of
more advanced
maintenance strategies
8© 2018 SAP SE or an SAP affiliate company. All rights reserved.
Multiple Approaches to Predictive MaintenanceData science driven approaches are on the rise
Asset
Conditio
n
TimeTotal Failure
Functional FailureAudible Noise
Ancillary Damage
Battery Impedance Test
Hot to Touch
Potential Failure = First Indication of Failure
Human
Driven
T
F
Equipment
Driven
Data Science Driven
Oil Analysis
X-ray Radiography
P Potential Failure
Why now?▪ IIoT/device connectivity
▪ Big data available for training models
▪ Declining hardware and software costs
▪ Massive computing powerP
P
P
More time to respond enables
greater flexibility to dynamically plan
maintenance events and to shift
unplanned to planned events
9© 2018 SAP SE or an SAP affiliate company. All rights reserved.
Company
Owns and operates a
fleet of around
2,000 electro-trains,
2,000 locomotives
and 30,000 coaches
and wagons
Customer ExampleTrain Operator
9CUSTOMER© 2017 SAP SE or an SAP affiliate company. All rights reserved. ǀ
40% of maintenance is currently reactive
The maintenance strategy proportions are for illustration purposes only and not reflective of actual customer percentages
Run to Failure Preventative Predictive*
*
10© 2018 SAP SE or an SAP affiliate company. All rights reserved.
Solution
Customer ExampleTrain Operator
10CUSTOMER© 2017 SAP SE or an SAP affiliate company. All rights reserved. ǀ
• Improve effectiveness
of maintenance
programs
• Data fusion between
IT and OT data
• Remote train
diagnostics
• Engineering rules and
predictive models
• Dynamic planning of
maintenance schedules
BRAKES
Energy Dissipation
versus Mileage
DOORS
Open/Closure Cycles &
Times
versus Mileage
• Higher asset availability & passenger satisfaction
• Projecting 100M Euro savings per year in
maintenance operations costs when fully
implemented
Benefits
Improved
Program
Effectiveness
Starting with
Improvements
to Preventative
Maintenance
Plans
Run to Failure Preventative Predictive
11© 2018 SAP SE or an SAP affiliate company. All rights reserved.
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
Failure Prediction
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
* Operational technology
SAP Predictive Maintenance and Service solutionFrom sensor to outcome
12© 2018 SAP SE or an SAP affiliate company. All rights reserved.
Service
Service Provider
Sales
Increase
customer
satisfaction
and loyalty
Dealer
Deliver the
value added
service at the
right price
Fleet
Owner/Operator
Decrease
maintenance
costs
Operator
Increase
asset up-time
R&D
Improve
asset
reliability
and up-time
Monitor
quality of
purchased
components
Improve
manufacturing
processes
Comply
with contract
service level
agreements
AftermarketProcurement Production
OEM
SAP Predictive Maintenance and ServiceDecision support across the ecosystem & asset lifecycle
DESIGN
BUILDSUPPORT
PURCHASE
OPERATE &
MAINTAINDISPOSE
Decision support to ALERT, DISCOVER AND REMEDY
Business DataMachine Data
Combining IT & OT data gives machine data context
13© 2018 SAP SE or an SAP affiliate company. All rights reserved.
SAP Predictive Maintenance and Service, on premise editionSolution 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
Analysis Tools Catalog
SAP Predictive Maintenance and Service
Explorer Equipment
Page
Logistics & Maintenance
Execution SystemsActions
Insights
Alerts
Raw
Data
Enables a data science driven
approach to condition monitoring
Flexible extension concept for
customers to build industry or
customer specific models and
analytics
A scalable Machine Learning
Engine that drives data science
insights into our business
processes
Flexible visualizations across
equipment structures
End-to-end process integration…
Alert, Discover, Remedy
14© 2018 SAP SE or an SAP affiliate company. All rights reserved.
SAP Predictive Maintenance and Service, on premise editionSystem and component level visualizations
Machine Learning Engine
Analysis Tools Catalog
SAP Predictive Maintenance and Service
Explorer (fleet view)
Explorer Equipment
Page
SAP Leonardo Foundation
SAP Leonardo for Edge Computing
SAP Leonardo Foundation
SAP Leonardo for Edge Computing
Logistics & Maintenance
Execution Systems
Business DataMachine Data
Equipment Page
15© 2018 SAP SE or an SAP affiliate company. All rights reserved.
SAP Predictive Maintenance and Service, on premise edition
Fiori Launchpad – ApplicationsProcess AppsExplorer
Performance Improvement
Obsolescence Management
...
Master Data AppsModels
Equipment
Locations
Spare Parts
Documents
Instructions
…
Machine Learning Engine AppsAlgorithms
Model Management
Admin AppsTemplates
Application Settings
...
16© 2018 SAP SE or an SAP affiliate company. All rights reserved.
Explorer
SAP Predictive Maintenance and Service, on premise editionExplorer - Analysis Tools Catalog
*”Health Status Overview” is an example of a custom Analysis Tool built using SDK
Health Status Overview
Health Status Overview
17© 2018 SAP SE or an SAP affiliate company. All rights reserved.
SAP Predictive Maintenance and Service, on premise editionExplorer
Analysis Tools Catalog
Explorer
Explorer
(Fleet View)
Analysis Tools Catalog
18© 2018 SAP SE or an SAP affiliate company. All rights reserved.
SAP Predictive Maintenance and Service, on premise editionExplorer
Key Figures Analysis ToolAnalysis Tools Catalog
Explorer
Explorer
(Fleet View)
Analysis Tools Catalog Analysis Tool
19© 2018 SAP SE or an SAP affiliate company. All rights reserved.
SAP Predictive Maintenance and Service, on premise editionExplorer
Equipment List Analysis ToolAnalysis Tools Catalog
Explorer
Explorer
(Fleet View)
Analysis Tools Catalog Analysis Tool
20© 2018 SAP SE or an SAP affiliate company. All rights reserved.
SAP Predictive Maintenance and Service, on premise editionExplorer
Analysis Tools Catalog
Explorer
Equipment Scores Analysis Tool
Explorer
(Fleet View)
Analysis Tools Catalog Analysis Tool
21© 2018 SAP SE or an SAP affiliate company. All rights reserved.
SAP Predictive Maintenance and Service, on premise editionExplorer
Map Analysis ToolAnalysis Tools Catalog
Explorer
Explorer
(Fleet View)
Analysis Tools Catalog Analysis Tool
22© 2018 SAP SE or an SAP affiliate company. All rights reserved.
SAP Predictive Maintenance and Service, on premise editionExplorer
Custom Analysis ToolAnalysis Tools Catalog
*”Health Status Overview” is an example of a custom Analysis Tool built using SDK
Explorer
Explorer
(Fleet View)
Analysis Tools Catalog Analysis Tool
23© 2018 SAP SE or an SAP affiliate company. All rights reserved.
Dissolved Gas Analysis using Duval Triangle/Pentagon as well as IEC Basic Gas Ratios methods
Utility-specific Insight Provider:
Oil Quality Analysis
24© 2018 SAP SE or an SAP affiliate company. All rights reserved.
Trend charts
Utility-specific Insight Provider:
Oil Quality Analysis
25© 2018 SAP SE or an SAP affiliate company. All rights reserved.
What is Machine Learning?Traditional Rule-Based Approach vs. Machine Learning
26© 2018 SAP SE or an SAP affiliate company. All rights reserved.
▪ Maintenance
and Ops data
▪ Telemetry data,
System faults
Machine Learning basics Process
Data
sources
▪ Technical
publications
▪ Design data
Prepare
input data
▪ Exploration
▪ Selection &
Transformation
▪ Cleaning &
Integration
Apply Machine
Learning ProcessOutput
SAP Predictive Maintenance and Service
Machine Learning Engine Analysis Tools
Train
Model
Configure
Model
Score
model
Feedback
Remaining
Useful LifeAnomaly
ScoreHealth
Status
2530 days
27© 2018 SAP SE or an SAP affiliate company. All rights reserved.
Machine Learning basics
Supervised Learning –
Failure Prediction
Unsupervised Learning -
Anomaly Detection
Input and output
variables (failures)
Algorithm learns
mapping function
from input variables
to output variable
Predictions made
when correlations
are found
between input
data and historic
failures
Trigger anomaly
alert when the
algorithm detects
an abnormal
pattern
Only input variables…
no output variable
Algorithm
learns normal
patterns from
input variables
Date Time Pressure Temperature Amperage RPM Failure event
Input Variables Target Variable
16-Apr 1:21 1003 154 220 1500 NO
16-Apr 1:22 1003 154 220 1500 NO
16-Apr 1:23 1003 154 255 1500 YES
Predicted failure
Date Time Pressure Temperature Amperage RPM
Input Variables Target Variable
17-Apr 1:21 1003 154 220 1500
17-Apr 1:22 1003 154 220 1500
17-Apr 1:23 1003 214 220 1500
Anomaly alert
28© 2018 SAP SE or an SAP affiliate company. All rights reserved.
SAP Predictive Maintenance and ServiceMachine Learning Engine
Apply Machine
Learning ProcessOutput
Machine Learning Engine Analysis Tools
Train
Model
Configure
Model
Score
model
Feedback
Remaining
Useful LifeAnomaly
ScoreHealth
Status
2530 days
SAP Predictive Maintenance and Service
Continuous Improvement & Learning
Failure
Prediction
Predictions made when
correlations are found
between input data and
historic failures
Anomaly Detection
Trigger anomaly alert
when the algorithm
detects an abnormal
pattern
New
Algorithms*
Extensibility
Model
Management
Adaptive
Learning*
Domain expert
feedback
Future capability*
29© 2018 SAP SE or an SAP affiliate company. All rights reserved.
SAP Predictive Maintenance and Service OPEMachine Learning Engine – Model Management
• Machine learning models are automatically applied to new incoming data
• Models are regularly re-trained using scheduling capabilities
• Model management capabilities allows us to maintain model versions
Configure model Score model
Deactivate
Train model
Retrain model
Model
ConfigurationModel Version Scores
Model
Management
Thank you.
Stephan Koenig
Product Management
SAP Digital Connected Assets,
Predictive Maintenance and Service
SAP SE
Dietmar-Hopp-Allee 16
69190 Walldorf
Phone: +49 6227 7 - 67939
Mail: [email protected]
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.
© 2018 SAP SE or an SAP affiliate company. All rights reserved.