April 21 - 10:00 AM ET and 3:00 PM ET
Presented by Gavin Jones, Principal Application Engineer
The use of computer simulations to analyze systems during the design process is a popular approach for validating and optimizing designs in the digital transformation of the manufacturing industry. But simulations are deterministic in nature and do not consider the uncertainty in design, manufacturing, and use of the product. Using Machine Learning and Uncertainty Quantification, engineers and data scientists can predict the range of possible outcomes for a given design accounting for such uncertainties. By building machine learning and predictive models of simulations, engineers and data scientists can efficiently perform advanced analytics and obtain new insights.
Using an ANSYS Fluent simulation of a T-joint, this presentation will provide an example of the above uses of machine learning and uncertainty quantification. Topics to be discussed will begin with the creation and use of a Design of Experiments (DOE) to select the best simulations to run for predictive model training data acquisition. This process is facilitated using SmartUQ’s ANSYS Workbench integration feature, which allows model parameters to be pulled directly into SmartUQ, the DOE submitted to Workbench for evaluation from within SmartUQ, and the simulation results automatically returned to SmartUQ. Results will include a sensitivity analysis and optimization of design parameters using the predictive model of the Fluent simulation and the propagation of uncertainties around the optimized solution.
