東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁 到查詢結果 [ null ]

切換: 標籤 | MARC模式 | ISBD

Model-Predictive and Machine Learnin...

Anjum, Mubtasim,

FindBook

Google Book

Amazon

博客來

Model-Predictive and Machine Learning-Based Control of Semi-Continuous Lentiviral Vector Production /

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Model-Predictive and Machine Learning-Based Control of Semi-Continuous Lentiviral Vector Production // Mubtasim Anjum.
作者:	Anjum, Mubtasim,
面頁冊數:	1 electronic resource (127 pages)
附註:	Source: Masters Abstracts International, Volume: 86-12.
Contained By:	Masters Abstracts International86-12.
標題:	Chemical engineering. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=32042809
ISBN:	9798280722682

Model-Predictive and Machine Learning-Based Control of Semi-Continuous Lentiviral Vector Production /
Anjum, Mubtasim,

Model-Predictive and Machine Learning-Based Control of Semi-Continuous Lentiviral Vector Production /Mubtasim Anjum. - 1 electronic resource (127 pages)

Source: Masters Abstracts International, Volume: 86-12.

In this work, I describe multiple process control strategies for a bioreactor for continuous lentiviral vector (LV) production using Lyapunov-based model predictive control (LMPC) and feedforward neural networks (FNN). Process control is an essential tool for meeting product specifications and maximizing yield in chemical and biological reactors. Lentiviruses or LVs are single-stranded RNA viruses that can infect cells to insert genetic payloads and that are highly valuable for gene therapy applications, sometimes costing up to $50,000 for a single dose. Currently, large-scale commercial production of LV is typically conducted in batches, a method that is costly and prone to batch-to-batch variability. Continuous production of LVs would significantly lower costs and minimize variability but has challenges such as the complexity of the bioreactor design, complicated process control, and limited bioreactor design parameters. In my work, I will address these challenges by incorporating LMPC and FNN models to control LV production in an iCellis nano bioreactor. The recent rise in artificial intelligence capabilities has prompted an interest in using neural networks for process control. Using previous studies on semi-continuous LV production, a model of the process system for LV production in a semi continuous fixed bed bioreactor was developed. An LMPC was created based on a process model to determine the best control action to maximize LV yield. The data from my LMPC model was then used to perform supervised training of an FNN model using TensorFlow module in Python. The results demonstrate that the LMPC can improve the production yield of LV production lightly (0.6%) and FNN can be effectively trained on LMPC-derived datasets for optimizing semi-continuous LV production.

English

ISBN: 9798280722682Subjects--Topical Terms:

560457
Chemical engineering.
Subjects--Index Terms:

Machine learning

Model-Predictive and Machine Learning-Based Control of Semi-Continuous Lentiviral Vector Production /
LDR:03261nmm a22004453i 4500 001 2435702
005 20251009122916.5
006 m o d
007 cr|nu||||||||
008 261011s2025 miu||||||m |||||||eng d
020 $a 9798280722682
035 $a (MiAaPQD)AAI32042809
035 $a AAI32042809
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Anjum, Mubtasim, $e author. $3 3826094
245 1 0 $a Model-Predictive and Machine Learning-Based Control of Semi-Continuous Lentiviral Vector Production / $c Mubtasim Anjum.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2025
300 $a 1 electronic resource (127 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: Masters Abstracts International, Volume: 86-12.
500 $a Advisors: Davis, Benjamin J.
502 $b M.E. $c The Cooper Union for the Advancement of Science and Art $d 2025.
520 $a In this work, I describe multiple process control strategies for a bioreactor for continuous lentiviral vector (LV) production using Lyapunov-based model predictive control (LMPC) and feedforward neural networks (FNN). Process control is an essential tool for meeting product specifications and maximizing yield in chemical and biological reactors. Lentiviruses or LVs are single-stranded RNA viruses that can infect cells to insert genetic payloads and that are highly valuable for gene therapy applications, sometimes costing up to $50,000 for a single dose. Currently, large-scale commercial production of LV is typically conducted in batches, a method that is costly and prone to batch-to-batch variability. Continuous production of LVs would significantly lower costs and minimize variability but has challenges such as the complexity of the bioreactor design, complicated process control, and limited bioreactor design parameters. In my work, I will address these challenges by incorporating LMPC and FNN models to control LV production in an iCellis nano bioreactor. The recent rise in artificial intelligence capabilities has prompted an interest in using neural networks for process control. Using previous studies on semi-continuous LV production, a model of the process system for LV production in a semi continuous fixed bed bioreactor was developed. An LMPC was created based on a process model to determine the best control action to maximize LV yield. The data from my LMPC model was then used to perform supervised training of an FNN model using TensorFlow module in Python. The results demonstrate that the LMPC can improve the production yield of LV production lightly (0.6%) and FNN can be effectively trained on LMPC-derived datasets for optimizing semi-continuous LV production.
546 $a English
590 $a School code: 0057
650 4 $a Chemical engineering. $3 560457
650 4 $a Biomedical engineering. $3 535387
650 4 $a Bioengineering. $3 657580
653 $a Machine learning
653 $a Lentiviral vector
653 $a Lyapunov-based model predictive control
653 $a Feedforward neural networks
653 $a Gene therapy
690 $a 0542
690 $a 0202
690 $a 0541
690 $a 0800
710 2 $a The Cooper Union for the Advancement of Science and Art. $b Chemical Engineering. $e degree granting institution. $3 3826095
720 1 $a Davis, Benjamin J. $e degree supervisor.
773 0 $t Masters Abstracts International $g 86-12.
790 $a 0057
791 $a M.E.
792 $a 2025
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=32042809