國立虎尾科技大學 |

Applications of Physics-Informed Machine Learning in Chemical Engineering.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Applications of Physics-Informed Machine Learning in Chemical Engineering./
作者:	Ansari, Mehrad.
面頁冊數:	1 online resource (159 pages)
附註:	Source: Dissertations Abstracts International, Volume: 85-03, Section: B.
Contained By:	Dissertations Abstracts International85-03B.
標題:	Chemical engineering. -
電子資源:	click for full text (PQDT)
ISBN:	9798380314978

Applications of Physics-Informed Machine Learning in Chemical Engineering.
Ansari, Mehrad.

Applications of Physics-Informed Machine Learning in Chemical Engineering. - 1 online resource (159 pages)

Source: Dissertations Abstracts International, Volume: 85-03, Section: B.

Thesis (Ph.D.)--University of Rochester, 2023.

Includes bibliographical references

Traditionally, testing of a given scientific hypothesis was hard due to the scarcity and limitations of the data that each experiment could produce. Today, experimental data collection at higher quantities, yet at lower relative costs has given a rise to data-driven modeling approaches. The main shortcoming of these black-box data-driven models is their complicated interpretability, mainly due to lacking a connection to the system's underlying physics. In contrast, physics-based models try to generate predictive data by solving complex mathematical formulations that are derived based on the conservation laws and physical principles. Regardless of their complexity, these models are still a proxy representation of a biased physical reality and in many cases, they fail at replicating the natural phenomena to the full extent. In this dissertation, the two approaches are combined over a variety of different problems relevant to chemical engineering, with the key idea of mitigating the disadvantages of using purely physics-based or data-driven models. This research demonstrates on flexibility of machine learning in application to computational fluid dynamics, epidemiological modeling, and peptide design.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9798380314978Subjects--Topical Terms:

555952
Chemical engineering.
Subjects--Index Terms:

CheminformaticsIndex Terms--Genre/Form:

554714
Electronic books.

Applications of Physics-Informed Machine Learning in Chemical Engineering.
LDR:02580ntm a22003857 4500 001 1144941
005 20240617111722.5
006 m o d
007 cr mn ---uuuuu
008 250605s2023 xx obm 000 0 eng d
020 $a 9798380314978
035 $a (MiAaPQ)AAI30529373
035 $a AAI30529373
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Ansari, Mehrad. $3 1470127
245 1 0 $a Applications of Physics-Informed Machine Learning in Chemical Engineering.
264 0 $c 2023
300 $a 1 online resource (159 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 85-03, Section: B.
500 $a Advisor: White, Andrew D.
502 $a Thesis (Ph.D.)--University of Rochester, 2023.
504 $a Includes bibliographical references
520 $a Traditionally, testing of a given scientific hypothesis was hard due to the scarcity and limitations of the data that each experiment could produce. Today, experimental data collection at higher quantities, yet at lower relative costs has given a rise to data-driven modeling approaches. The main shortcoming of these black-box data-driven models is their complicated interpretability, mainly due to lacking a connection to the system's underlying physics. In contrast, physics-based models try to generate predictive data by solving complex mathematical formulations that are derived based on the conservation laws and physical principles. Regardless of their complexity, these models are still a proxy representation of a biased physical reality and in many cases, they fail at replicating the natural phenomena to the full extent. In this dissertation, the two approaches are combined over a variety of different problems relevant to chemical engineering, with the key idea of mitigating the disadvantages of using purely physics-based or data-driven models. This research demonstrates on flexibility of machine learning in application to computational fluid dynamics, epidemiological modeling, and peptide design.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Chemical engineering. $3 555952
650 4 $a Fluid mechanics. $3 555551
653 $a Cheminformatics
653 $a Machine learning
653 $a Peptide design
653 $a Simulation-based Inference
653 $a Physical principles
655 7 $a Electronic books. $2 local $3 554714
690 $a 0542
690 $a 0204
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a University of Rochester. $b Hajim School of Engineering and Applied Sciences. $3 1148592
773 0 $t Dissertations Abstracts International $g 85-03B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30529373 $z click for full text (PQDT)