|About this Abstract
||2019 TMS Annual Meeting & Exhibition
||Computational Approaches for Big Data, Artificial Intelligence and Uncertainty Quantification in Computational Materials Science
||M-9: Sequential Experiments Design for Acceleration the Developments of NiTi-based Shape Memory Alloys
||Sen Liu, Behnam Amin-Ahmadi, Branden Kappes, Aaron Stebner, Xiaoli Zhang
|On-Site Speaker (Planned)
Because the time intensity of performing experiments and high dimensionality of experiments design space in manufacturing processes, the experiments exploring on entire design space is often prohibitively costly and time-consuming. To accelerate the development of NiTi-based shape memory alloys, it proposed a sequential experiments design framework to strategically identify the experiments candidate in sequence, to maximize information gain using fewest possible number. A Kriging regression model scales to high-dimensional search space in terms of processing features, part properties and alloy compositions. An active selector based on Maximum Expected Improvement (MEI) strategy was used to pick experiments candidate by balancing the exploring highly-uncertain candidates and exploiting highly-performing candidates. The developed framework can effectively guide the practitioner to test the most promising candidates (i.e. processing parameters and/or material compositions) earlier for achieving desirable designed properties, in such a way greatly reducing the time and costs for developments of NiTi-based shape memory alloys.
||Planned: Supplemental Proceedings volume