Apply Digital Twin technology to realize data-driven maintenance by creating digital copies of your assets & processes and run real-time predictive analytics on them in a digitally secure way.
3. UReason
Software Solutions for Condition Based and
Predictive Maintenance
Domain & software knowledge combined
Main offices in the Rotterdam (NL) and Reading
(UK)
From Data to Solutions !
4. Use Cases & Business Cases Data Collection Model Development Architecture & APM Software
We Support our Customers In
Development of condition monitoring and predictive maintenance solutions
New digital service models
Process optimization: costs, efficiency, uptime, control
Digitize the knowledge of experienced operator, maintenance and engineering teams
5. Same Capability At Different Levels
Operator/OEM Cloud Enterprise/Site Data On-premise/Cloud
Diagnosis, Prognosis,
Benchmarking,
Optimisation
CMMS/ERP Planning Data PC/Server/Cloud
Optimize
Maintenance
Planning/Cost
MES/Historians Aggregated Data PC/Server Optimize Process
SCADA/DCS Low Frequency Data PC/Server
Monitor Faults –
Relations to Process
PLC/Controller Control Data Edge
Optimize Control
Run CBM/PdM
Instrumentation/
Actuators/Assets
High Frequency Data Embedded Monitor Faults/Risks
APM
Focus
APM Typical
Deployment
L5
L4
L3
L2
L1
L0
6. Digital Twins .. Everywhere .. What is it?
“Digital twins are becoming a business imperative, covering the
entire lifecycle of an asset or process and forming the foundation
for connected products and services. Companies that fail to respond
will be left behind.” – Thomas Kaiser, SAP Senior Vice President of
IoT
“The concept is exciting, absolutely, but more complex than one can
be led to believe. Today there is a naiveté in many companies about
the cost and time aspects.” – Marc Halpern, Gartner Analyst
13% of organizations implementing Internet of Things (IoT) projects already use digital twins,
while 62% are either in the process of establishing digital twin use or plan to do so. – Gartner
Survey 2019
7. Digital Twin
Source: Gartner
A digital twin is a digital representation of a real-world entity or system. The implementation of a digital
twin is an encapsulated software object or model that mirrors a unique physical object, process,
organization, person or other abstraction. Data from multiple digital twins can be aggregated for a
composite view across a number of real-world entities, such as a power plant or a city, and their related
processes.
Inputs
Real World Objects
Processing –
Simulate/Predict
Outputs
(To act upon)
8. Types of Digital Twins
Process Twin
System/Unit Twin
Asset Twin
Component Twin
Field Services
Management
Designers
Product Managers
Marketing/Sales
Manufacturing Process
Crude Unit, Cooling Unit , …
Turbine, Motor, Valve …
Bearing, Piston, Axle, …
9. Elements of a Digital Twin
1) Physical Equipment
2) Twin Model
3) Knowledge
(Data)
4) Analytics
10. Qualifying Criteria for Digital Twins
Criteria to consider for Digital Twins and Data Driven Maintenance:
1. Data from field level can be extracted and enhanced to provide further insights
higher in the chain.
2. The problem must be support business case, meaning there should be a target or
an outcome to predict/calculate that is of value to operations.
3. Preferably the problem should have a record of the operational history of the
equipment that contains both good and bad outcomes.
4. The business should have domain experts who have a clear understanding of the
problem.
11. Steps to Realise Digital Twins
Qualify
& Define
Build
Validate
Deploy
Maintain
Update
Improve
Business Case
Delivery Scope
Organization Support
Real-time Data
Historical Data
Knowledge
Criteria
Monitor Performance
Embed in Processes
Organizational Support
16. Q&A
joudmans@ureason.com Jules Oudmans
Contact me for:
Further questions!
Demo APM Studio
Examples and references
Discussing Use Cases
Knowledge Sharing for example on Strategy, Architecture, Edge
computing, Device Analytics, ..
Editor's Notes
Hello everyone welcome to this webinar hosted by UReason.
In this webinar I will explain what Digital Twins are and how you can apply Digital Twins in the world of Data Driven Maintenance.
This webinar consists of four parts:
First, I will briefly introduce the company UReason
After this I will go into detail on the different types of Digital Twins, the elements that make a Digital Twin and criteria for Digital Twins to be used in Data Driven maintenance initiatives
Then we go into APM Studio to look into a life example of Digital Twins
And this is followed by a Q&A session
I am Jules Oudmans presenting to you today
I have a background in AI starting in the nineties and have been involved many times in the past 25 years in prognostic and predictive programs that ensure asset integrity for critical assets and critical processes
Here are my contact details .. If you have questions after the webinar don’t hesitate to e-mail me.
I work at UReason, a software company, that provides solutions for real-time condition based and predictive maintenance and I help our customers daily to use our software – from data analysis to the set-up of applications and solutions that monitor important assets and processes.
At UReason we combine our domain expertise and software knowledge with our customers and I help them from data to solutions.
We have offices in Rotterdam, which we see here in the picture, and Reading in the UK.
Our customers are predominantly in the manufacturing and process industry and the majority of them are located in Western Europe and North Americas.
UReason is active in the real-time condition monitoring, predictive and prescriptive maintenance domain.
Our field of operation is from helping customers to insights into data to helping Asset Owners, OEMs and maintenance service organisations with data driven maintenance solutions.
Often we start together with our customers to define the business case and use-cases to focus on, followed by data collection, model development and deploying the solutions into the existing OT and IT landscape.
Our software, APM Studio, is used at different levels in the automation pyramid
Embedded – with OEMS – monitoring Faults and Risks in ‘isolation’ to the asset. An Asset can be instrumentation an actuator or a pump, compressor, filter et cetera
At the Edge … processing asset data of one or multiple assets to run condition monitoring and predictive applications near to where the data is generated.
AND we also work at Level-2/Level-3 where APM is used to monitor faults in relationship to the process, deployed/running on on-premise compute
When deployed at Level-4 and Level 5 APM-Studio is used for optimizing the maintenance costs and planning associated to an asset base supporting a process.
So in today’s webinar I want to introduce the topic of Digital Twins.
[PAUZE]
Digital Twins get a lot of attention in the media … and I would like to break down in this webinar what a Digital Twin means and how to apply it in the world of Data Driven Maintenance.
[INTERACTION]
Before we start going deeper into the topic of Digital Twins let me ask you a question to better understand where you currently are in your understanding and perhaps also usage of Digital Twins:
We are not using Digital Twins yet
We are investigating the use of Digital Twins
We are using Digital Twins
Digital Twin technology brings an exact replica in digital format, so in software format, of a process, a product, or a service. Basically, it takes real-world data about a physical object or system as inputs, and produces outputs in the form of predictions or simulations of how that physical object or system will be affected by those inputs.
The most common use case for digital twins are:
Visualization of products in use, by real users, in real-time
Troubleshooting of remote or inaccessible equipment
Managing complexities and linkage within systems-of-systems
Connecting disparate systems and promoting traceability
There are different types or levels of Digital Twins and these have different Use Case Scenarios:
The Component Twin for example a Bearing, Piston, Axle : Can support field services/technicians to continuously monitor and offer predictive maintenance insights while reducing equipment downtime (planned and unplanned) and enable service-based business models.
An Asset Twin for example a Turbine, Motor, Control Valve: Can support product management, sales to gather knowledge on customer’s preferences and actual usage of their product and provide new service business models to drive revenue.
System / Unit Twin For example a Crude or Reverse Osmosis Unit: Helps product designers, architects, and engineers to improve future product versions and engineering models to optimize product performance and efficiency, accelerating time-to-market.
Process Twin For example a Composite Manufacturing Process: Helps management to get new operational data feeds into production and planning models thus paving way for strategic insights, recommendations, and road maps.
A Digital Twin consists of 4 main elements:
The Physical equipment - the actual equipment item or items that we are interested in creating a twin for.
The Twin Model – The software model consisting of a hierarchy of systems, sub-assemblies, and components that describe the twin and its characteristics enriched by asset, operational, historical, and context data.
Knowledge - Data sources that feed the twin with operational settings, domain expertise, historical data, and industry best practices.
Analytics – Simulation and/or Machine Learning models these can be physics-based models, statistical models, and machine learning/AI models to help describe, predict and prescribe the behavior (current and future) of the asset, system, or process.
In the screenshots in this slide I am showing various parts of our software, APM Studio, that is used to set-up digital twins
INTERACTION: Let me ask you a question
Have you started or do you want to start with a Digital Twin program:
I have started
I have started but need assistance
I want to start
I want to start but I do not know how to start best
No I have not
No I will not
Not all use cases or business problems can be effectively solved by predictive maintenance using a Digital Twin. They are not a cure to all illnesses.
The important qualifying criteria that you need to consider during use case qualification for Digital Twin projects are:
An obvious one; Data from field level can be extracted and enhanced to provide further insights higher in the chain.
The problem must be support business case, meaning there should be a target or an outcome to predict/calculate that is of value to operations.
Preferably the problem should have a record of the operational history of the equipment that contains both good and bad outcomes.
Finally, the business should have domain experts who have a clear understanding of the problem.
The steps to realize Digital Twins are quite logical.
Think before you begin .. It is not about trying new technology but selecting a Digital Twin that provides value to your organization/business and or customers.
Value can be reduction of planned maintenance, creating longer preventive maintenance time horizons, knowing hourly/daily what the risk and associated cost of operation is etc cetera
The next step is to build and realize the Digital Twin. What we saw in the previous slides is that you need access to data streams (access to the data from the physical asset), historical data, knowledge/simulation models and criteria – for example I want to now where on the PF curve may asset currently is. Validation is off course key (hence why you need historical data).
Once successfully validated you can deploy and embed the DT in your processes, but you do need to monitor its performance/deviations and embed the life-cycle management of your Digital Twins in your organisation.
So we will have a look at how we can set-up Digital Twins in APM Studio and create Digital copies that can be run at different levels in your automation or cloud infrastructure.
But before I switch to the live demonstration let me first give you an overview of what we will look at in the live demo
I will now switch to the live demonstration.
That concluded the demo but I do want to provide some extra food for thought
Here an example of DT
Device in the field, communicating HART
Analytics and Preprocessing of data at Edge level
Secure Communication from Edge Level to Cloud or MES/IT layer and Closing the loop with the organisation
[CLICK]
Realising a NOA 175 – Namur Open Architecture implementation
…
[INTERACTION]
Let me ask you one more question:
Would you be interested to learn more about how you can use Digital Twins to monitor your assets and processes
Yes
Perhaps, I need further information
No
Thanks for your inputs …. With the demo ending we have come to the end of this webinar .. But do not go yet. We have the Q&A coming up
If you do need to go please leave us your feedback via the evaluation form – see the link in the chat window.
Carlos can you show me the questions from the audience ..
Before we go to the questions and answers I would like to point you to the maturity scan that we have online now on our website. This scan provides you an understanding of your maturity towards data-driven maintenance and how you benchmark against the industry and where you can improve.
It takes you 10 minutes to fill-in
--- questions ..
Ok that was the last question, thank you very much from my side for listening and asking interesting questions. Here are my contact details and please note that after the webinar you will receive the slides and a link to the replay.
Again we appreciate your feedback .. please leave us your feedback via the evaluation form – see the link in the chat window.
I wish you a nice day and maybe we'll see you in one of our next webinars.