| LDR | | 00000nam u2200205 4500 |
| 001 | | 000000434091 |
| 005 | | 20200226140757 |
| 008 | | 200131s2019 ||||||||||||||||| ||eng d |
| 020 | |
▼a 9781088385654 |
| 035 | |
▼a (MiAaPQ)AAI22616320 |
| 040 | |
▼a MiAaPQ
▼c MiAaPQ
▼d 247004 |
| 082 | 0 |
▼a 620.11 |
| 100 | 1 |
▼a Menon, Aditya. |
| 245 | 10 |
▼a Development of Hierarchical Machine Learning for the Modeling and Design of Complex Material Systems. |
| 260 | |
▼a [S.l.]:
▼b Carnegie Mellon University.,
▼c 2019. |
| 260 | 1 |
▼a Ann Arbor:
▼b ProQuest Dissertations & Theses,
▼c 2019. |
| 300 | |
▼a 181 p. |
| 500 | |
▼a Source: Dissertations Abstracts International, Volume: 81-03, Section: B. |
| 500 | |
▼a Advisor: Washburn, Newell R. |
| 502 | 1 |
▼a Thesis (Ph.D.)--Carnegie Mellon University, 2019. |
| 506 | |
▼a This item must not be sold to any third party vendors. |
| 520 | |
▼a The overarching objective of this study was to develop a methodology for optimization of system responses in complex material systems with small datasets utilizing machine learning/statistical techniques with domain specific system data. These systems are ubiquitous in various large-scale materials industries like detergents, food packaging, agrochemicals, cement to small scale and emerging sectors like 3D printing etc. The algorithm developed in this research is referred to as Hierarchical Machine Learning (HML). As part of this study, disparate material systems have been optimized and validated in three major categories of system variables-molecular design, formulation and processing. Molecular design was validated using HML by (a) developing a novel superplasticizer for a non-setting cement model (MgO) and then (b) developing a novel superplasticizer for a Metakaolin-Portland cement blend to improve rheological behavior (slump). Process optimization was validated using HML on a silicone 3D printing system by improving print speed and diversity without degradation of print fidelity. Formulations optimization was validated using HML on a system of polyurethane films with varying polyols and diisocyanate reactants and varying NCO: OH index for prediction of mechanical responses, strain at break, stress at break and Tan 灌 with a further purpose of enabling prediction for substituted reactants and categorical responses. Based on these studies, it is shown that HML can be used to gain physical insight from a material system with a small and high-quality dataset while enhancing the predictive capability of the system. This methodology can then be extended to optimize the system for desired complex responses. |
| 590 | |
▼a School code: 0041. |
| 650 | 4 |
▼a Engineering. |
| 650 | 4 |
▼a Polymer chemistry. |
| 650 | 4 |
▼a Materials science. |
| 690 | |
▼a 0537 |
| 690 | |
▼a 0794 |
| 690 | |
▼a 0495 |
| 710 | 20 |
▼a Carnegie Mellon University.
▼b Materials Science and Engineering. |
| 773 | 0 |
▼t Dissertations Abstracts International
▼g 81-03B. |
| 773 | |
▼t Dissertation Abstract International |
| 790 | |
▼a 0041 |
| 791 | |
▼a Ph.D. |
| 792 | |
▼a 2019 |
| 793 | |
▼a English |
| 856 | 40 |
▼u http://www.riss.kr/pdu/ddodLink.do?id=T15493379
▼n KERIS
▼z 이 자료의 원문은 한국교육학술정보원에서 제공합니다. |
| 980 | |
▼a 202002
▼f 2020 |
| 990 | |
▼a ***1008102 |
| 991 | |
▼a E-BOOK |