A Maximum Entropy Approach for Uncertainty Quantification and Analysis of Multifunctional Materials
Publication Type:
Conference
Authors:
Wei Gao and William Oates
Co-Authors:
Ralph Smith
Year Published:
2017
Abstract:
The Maximum Entropy (ME) method is shown to provide a new approach for quantifying model uncertainty in the presence of complex, heterogeneous data. This is important in model validation of a variety of multifunctional constitutive relations. For example, multifunctional materials contain field-coupled material parameters that should be self-consistent regardless of the measurement. A classical example is piezoelectricity which may be quantified from charge induced by stress or strain induced by an electric field. The proposed tools provide new statistical information to address measurement discrepancies, guide model development, and catalyze materials discovery for data fusion problems. The error between the model outputs and heterogeneous data is quantified and used to formulate a second moment constraint within the entropy functional. This leads to an augmented likelihood function that weights each individual set of data by its respective variance and covariance between each data set. As a first step, the method is evaluated on a piezoelectric ceramic to illustrate how the covariance matrix influences piezoelectric parameter estimation from heterogeneous electric displacement and strain data.
Conference Name:
ASME 2017 Conference on Smart Materials, Adaptive Structures and Intelligent Systems
Conference Location:
Snowbird, Utah, USA
Other Numbers:
Refereed Designation:
Date Published:
9/18/2017