The use of Physics Based Predictive Analytics in Digital Twins. Frode Halvorsen, PhD Vice President Technology

Transcription

1 The use of Physics Based Predictive Analytics in Digital Twins Frode Halvorsen, PhD Vice President Technology

2 Outline Business motivation Enabling technology Customer cases

3 IoT Value Chain Smart Product Sensors Connectivity Platform Applications Customer

4 Industrial IoT by EDRMedeso + +

5 Time to develop Time to develop Analytics Solutions Condition Based Analytics Condition & Prediction Based Analytics Use Historical Data to Predict Asset Behavior in the future Understand the health of asset Understand the health of asset Analyze Real Time Data Analyze the Real Time Data Collect Data Collect the Data Connect Asset Connect the Asset Market Value Market Value

6 Analytics Solutions Use-Cases Data Definition Algorithm Definitions Implementation Fill the Data Lake Modelling Product 3-10 Years Copyright EDR & Medeso AS 2016

7 Accelerated Physics Based Solutions Use-Cases Data Definition Algorithm Definitions Generate Data via Simulation Algorithmic Modelling Implementation Product Weeks Copyright EDR & Medeso AS 2016

8 The Digital Twin Unpredictive Physical unit Sensor on physical unit Real time analytics Condition based Traffic light indicators Realtime Future Predictive Digital twin Sensor on physical unit Analysis Predicting maintenance and failure Trigger ROM Full 3D

9 Implementation BLE Mesh Mobile WiFi Ethernet SmartTags Local Gateway(s) Cloud connect API Copyright EDR & Medeso AS 2016

10 450 Vibration rms [mg] Copyright EDR & Medeso AS 2016

11 Operational Output Copyright EDR & Medeso AS 2016

12 Digital Prototypes Wind Angle Rotational speed Current sweep Position sweep Power Voltage/Current Q U A L I T Y Wind Velocity Mechanical loads Displacements Damage? M A I N T E N A N C E

13 free Traversing Physical Model Fidelity to here? a b c PMSM mech_rv System-Level Behavior Equation / Data-Based How to get from here Reduced-Order Modeling A simplification of a high-fidelity dynamical model that preserves essential behavior and dominant effects, High-Fidelity 3D Physics for the purpose of reducing solution time or storage capacity required for the more complex model.

14 Secondary Inlet Temperature (K) Temperature Field ( C) 3 SVD modes only need to reconstruct the unsteady temperature field A temperature signal excitation is provided to cover the full temperature spectrum ANSYS DYNAROM Step 1 Fluent Time (s) Verification of the Dynarom model created Dynarom

15 Secondary Inlet Temperature (K) Temperature Field ( C) Step 2 Arbitrary temperature field Fluent Time (s) Dynarom

16 ANSYS Twin Builder:

17 Digital Prototype Rotor speed Control feedback Controling TSR Tip Speed Ratio Setpoint TSR (Ratio between blade tip speed and wind speed) Pitch angle Control Signal Wind speed Wind direction

18 Digital Twins

19 ANSYS Digital Twins in the Cloud

20

21 Grundfos SYSMON digital twins - harness the power of IoT to optimize your life. Grundfos, a global leader in design and manufacturing of pumps and water systems, brings advanced simulation and prediction capabilities to real-time in collaboration with simulation-powerhouse ANSYS and elite channel partner EDRMedeso. Grundfos will use digital twins to better serve its customers through improved product quality and performance, enhanced development productivity, optimized maintenance and reduced overall costs and risks associated with unplanned downtime.

22 Main Takeaways The key technologies are ready; implementation can start tomorrow Commercial solutions available on the market Physics based analytics offers an accelerated process compared to most predictive analytics Established and proven methods can be applied in new areas Numerous use cases already implemented; first runners are running