東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Mechanistic Intelligent Digital Twin...

Xie, Xiaoyu,

Linked to FindBook

Google Book

Amazon

博客來

Mechanistic Intelligent Digital Twin for Process Monitoring and Defect Mitigation in Additive Manufacturing /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Mechanistic Intelligent Digital Twin for Process Monitoring and Defect Mitigation in Additive Manufacturing // Xiaoyu Xie.
Author:	Xie, Xiaoyu,
Description:	1 electronic resource (135 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 86-12, Section: B.
Contained By:	Dissertations Abstracts International86-12B.
Subject:	Mechanical engineering. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=32038476
ISBN:	9798315797838

Mechanistic Intelligent Digital Twin for Process Monitoring and Defect Mitigation in Additive Manufacturing /
Xie, Xiaoyu,

Mechanistic Intelligent Digital Twin for Process Monitoring and Defect Mitigation in Additive Manufacturing /Xiaoyu Xie. - 1 electronic resource (135 pages)

Source: Dissertations Abstracts International, Volume: 86-12, Section: B.

Additive manufacturing involves complex, multi-physics interactions-such as melt pool dynamics, keyhole formation, and defect evolution-that are highly sensitive to process conditions and material properties. Real-time prediction and interpretation of these phenomena remain challenging due to their transient, localized, and strongly coupled nature. Advances in artificial intelligence, in-situ sensing, and computational hardware offer new opportunities for predictive analytics and autonomous control. However, a unified framework that effectively integrates physical knowledge, sensor data, and computational intelligence for real-time monitoring and control has yet to be established.This dissertation introduces the Mechanistic Intelligent Digital Twin (MIDT)-a hybrid modeling framework that combines physics-based simulations, data-driven learning, and real-time sensor feedback. Unlike conventional digital twins that rely primarily on historical data or computationally intensive solvers, MIDT embeds physical laws and mechanistic insights directly into its architecture, enabling it to learn from data while maintaining physical consistency. This allows it to bypass the traditional process-structure-performance relationship and directly infer internal phenomena and material properties under evolving conditions.The MIDT framework addresses three core challenges: (1) learning melt pool dynamics from high-dimensional, noisy, multimodal sensing data; (2) predicting keyhole behavior and porosity from limited experimental observations while discovering underlying physical laws; and (3) ensuring real-time responsiveness for process control. To overcome these barriers, this work develops a statistical multi-task model for sensor-driven monitoring, a physics-based dimension reduction method for mechanistic insight discovery, and a multi-fidelity digital twin model for layer-wise thermal control. Together, these contributions demonstrate how mechanistic intelligence can transform digital twins into interpretable, autonomous, adaptive systems-capable of optimizing performance, reducing defects, and advancing toward fully autonomous manufacturing.

English

ISBN: 9798315797838Subjects--Topical Terms:

649730
Mechanical engineering.
Subjects--Index Terms:

Additive manufacturing

Mechanistic Intelligent Digital Twin for Process Monitoring and Defect Mitigation in Additive Manufacturing /
LDR:03671nmm a22004333i 4500 001 2432721
005 20250731101919.5
006 m o d
007 cr|nu||||||||
008 261011s2025 miu||||||m |||||||eng d
020 $a 9798315797838
035 $a (MiAaPQD)AAI32038476
035 $a AAI32038476
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Xie, Xiaoyu, $e author. $3 3822051
245 1 0 $a Mechanistic Intelligent Digital Twin for Process Monitoring and Defect Mitigation in Additive Manufacturing / $c Xiaoyu Xie.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2025
300 $a 1 electronic resource (135 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: 86-12, Section: B.
500 $a Advisors: Liu, Wing Kam Committee members: Wagner, Gregory; Apley, Daniel; Qian, Dong.
502 $b Ph.D. $c Northwestern University $d 2025.
520 $a Additive manufacturing involves complex, multi-physics interactions-such as melt pool dynamics, keyhole formation, and defect evolution-that are highly sensitive to process conditions and material properties. Real-time prediction and interpretation of these phenomena remain challenging due to their transient, localized, and strongly coupled nature. Advances in artificial intelligence, in-situ sensing, and computational hardware offer new opportunities for predictive analytics and autonomous control. However, a unified framework that effectively integrates physical knowledge, sensor data, and computational intelligence for real-time monitoring and control has yet to be established.This dissertation introduces the Mechanistic Intelligent Digital Twin (MIDT)-a hybrid modeling framework that combines physics-based simulations, data-driven learning, and real-time sensor feedback. Unlike conventional digital twins that rely primarily on historical data or computationally intensive solvers, MIDT embeds physical laws and mechanistic insights directly into its architecture, enabling it to learn from data while maintaining physical consistency. This allows it to bypass the traditional process-structure-performance relationship and directly infer internal phenomena and material properties under evolving conditions.The MIDT framework addresses three core challenges: (1) learning melt pool dynamics from high-dimensional, noisy, multimodal sensing data; (2) predicting keyhole behavior and porosity from limited experimental observations while discovering underlying physical laws; and (3) ensuring real-time responsiveness for process control. To overcome these barriers, this work develops a statistical multi-task model for sensor-driven monitoring, a physics-based dimension reduction method for mechanistic insight discovery, and a multi-fidelity digital twin model for layer-wise thermal control. Together, these contributions demonstrate how mechanistic intelligence can transform digital twins into interpretable, autonomous, adaptive systems-capable of optimizing performance, reducing defects, and advancing toward fully autonomous manufacturing.
546 $a English
590 $a School code: 0163
650 4 $a Mechanical engineering. $3 649730
650 4 $a Mechanics. $3 525881
650 4 $a Materials science. $3 543314
653 $a Additive manufacturing
653 $a Mechanistic Intelligent Digital Twin
653 $a Autonomous manufacturing
653 $a Mechanistic insights
653 $a Real-time prediction
690 $a 0548
690 $a 0346
690 $a 0794
710 2 $a Northwestern University. $b Mechanical Engineering. $e degree granting institution. $3 3822052
720 1 $a Liu, Wing Kam $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 86-12B.
790 $a 0163
791 $a Ph.D.
792 $a 2025
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=32038476