Developing an Embedded Digital Twin for HVAC Device Diagnostics Gianluca Bacchiega R&D manager at I.R.S. ni.com
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 For every physical asset in the world, we have a virtual copy running in the cloud that gets richer with every second of operational data Ganesh Bell, chief digital officer and general manager of Software & Analytics at GE Power & Water Digital twin Explosion: billions of twins in next five years
an Engineering Company
1 Digital twin: what? 2 4 3 Embedded digital twin for HVAC diagnostic A twin using model technology 4.0 Value and ROI of digital twins 5 Conclusion
Digital twin: what? ni.com
A digital twin is a real-time digital replica of a physical device.
A digital twin is a real-time digital replica of a physical device. chiller chiller digital twin It s more than a model
A digital twin is a real-time digital replica of a physical device. Sensors Model digital twin Sensors
A simple digital replica? History Log the device history digital twin Future Forecast device future Sensors
A bridge between the physical and digital world Physical device Data acquisition Sensors
A bridge between the physical and digital world Monitoring Machine Learning & Models Big data
A bridge between the physical and digital world Digital Twin Physical devices Data acquisition Monitoring Machine Learning & Models Sensors Big data
Embedded Digital Twin for HVAC diagnostic ni.com
We developed an Embedded Digital Twin Physical devices Data acquisition Monitoring Machine Learning & Models Sensors embedded digital twin Big data Sensors
for HVAC Device Diagnostics Physical devices Data acquisition Monitoring Machine Learning & Models Sensors embedded digital twin Big data Sensors Fault Detection and Diagnosis
From monitoring to embedded digital twin 1. Lifelong Device history 2. Real time model computed virtual sensor 3. Real Time predictive alert
A twin using model technology 4.0 ni.com
Model technology 4.0 Physical Model Machine learning Fluid properties Components Phenomena DAQ correction Compressor Heat transfer Heat exchangers Mass transfer Fans embedded digital twin
HVAC Physical Model Physical Model Fluid properties Components Phenomena DAQ correction The phenomenological model, based on equations, Compressor Heat exchangers Heat transfer Mass transfer embedded digital twin can identify the causes of a possible malfunction Fans
Machine learning Unsupervised data Supervised data Feature extraction Machine learning algorithm The machine learning approach needs no detailed knowledge about machine operation. New data Predictive model It needs a learning phase to be able to predict the system performance.
Diagnostic detail and easy implementation Sensor Data Physical Physical Model Model Machine Learning Test system Fluid properties Components Phenomena DAQ correction Compressor Heat transfer Heat exchangers Mass transfer Fans
Merging model technology using NI platform LabVIEW Machine Learning Toolkit embedded digital twin
Value and ROI of digital twins ni.com
A bridge between the physical and digital world with Value and ROI embedded Understand using a learning model Enhance add virtual sensors Warn on health & efficiency Maintain & log the entire life of an asset Predict Failure and Optimize Digital Twin
Value and ROI of digital twins Maintain & log the entire life of an asset
Value and ROI of digital twins Understand by learning model #1 #2 #3 #4... #5 #N
Value and ROI of digital twins Enhance add virtual sensors Temperature Pressure Flow Efficiency & Power consumption Thermodynamic cycle point
Value and ROI of digital twins Warn on health & efficiency Digital twin
Value and ROI of digital twins Predict failure Optimize Predict Failure and Optimize
Conclusion ni.com
Conclusion : smart monitoring Machine level Plant level Company level Customer level Sensors Edge computing & gateway Cloud & Analytics Smart client & Augmented reality Measure Acquire, control & model Aggregate, understand & publish View
Conclusion: Artificial Intelligence and physical model Intelligence at the edge Raw Data Data Mining Predictive model RT Test system System training decided by the operator Machine Learning
Implement digital twin using NI platform and partner like n
Thank you for your attention. any question or inquiry info@irsweb.it