Is this project an undergraduate, graduate, or faculty project?
Graduate
Project Type
individual
Campus
Daytona Beach
Authors' Class Standing
Graduate Student
Lead Presenter's Name
Naresh Ahuja
Faculty Mentor Name
Dr. Mandar Kulkarni
Loading...
Abstract
Jet Aircraft Engines turbine blades, Rocket engines, Missiles, re-entry vehicles strive to improve performance. Ceramic Matrix composites (CMC’s) replace Nickel Super-alloys because of the numerous novel advantages as weight reduction, operating at higher temperatures, producing higher thrust by reducing the cooling air diverted from thrust. The traditional material science engineering takes a long time to generate these advanced ceramic matrix composite with the tailored required performance. With the rapid development of machine learning, it is possible to use neural network to build models to predict the performance of CMC’s. A reduced order, data driven, predictive model to quantify the creep strength in continuous CMC using the machine learning tools is proposed and explored. A framework is developed to quantify the importance of microstructural parameters on strength. The stochastic microstructure attributes considered includes the fiber diameter, fiber spacing, interface material, interface thickness and volume fraction. The elastic responses of the instantiated microstructures are characterized using finite element analysis (FEA). Results from the FEA will be used as the ground truth to calibrate and validate a data-driven machine learning (ML) model. The quantified stochastic microstructure attributes will be correlated with the statistics of the simulated response. The predictive capabilities of the model for a new microstructure will be demonstrated.
Did this research project receive funding support (Spark, SURF, Research Abroad, Student Internal Grants, Collaborative, Climbing, or Ignite Grants) from the Office of Undergraduate Research?
No
Predicting the effects of microstructure on creep strength in Ceramic Matrix Composite using Data driven Modelling
Jet Aircraft Engines turbine blades, Rocket engines, Missiles, re-entry vehicles strive to improve performance. Ceramic Matrix composites (CMC’s) replace Nickel Super-alloys because of the numerous novel advantages as weight reduction, operating at higher temperatures, producing higher thrust by reducing the cooling air diverted from thrust. The traditional material science engineering takes a long time to generate these advanced ceramic matrix composite with the tailored required performance. With the rapid development of machine learning, it is possible to use neural network to build models to predict the performance of CMC’s. A reduced order, data driven, predictive model to quantify the creep strength in continuous CMC using the machine learning tools is proposed and explored. A framework is developed to quantify the importance of microstructural parameters on strength. The stochastic microstructure attributes considered includes the fiber diameter, fiber spacing, interface material, interface thickness and volume fraction. The elastic responses of the instantiated microstructures are characterized using finite element analysis (FEA). Results from the FEA will be used as the ground truth to calibrate and validate a data-driven machine learning (ML) model. The quantified stochastic microstructure attributes will be correlated with the statistics of the simulated response. The predictive capabilities of the model for a new microstructure will be demonstrated.