Many-objective process optimisation with constraints for continuous tableting lines: a case study in lovastatin

Kai Eivind Wu; Cameron J. Brown; Murray N. Robertson; Blair F. Johnston; George Panoutsos

Many-objective process optimisation with constraints for continuous tableting lines: a case study in lovastatin

Kai Eivind Wu, Cameron J. Brown, Murray N. Robertson, Blair F. Johnston, George Panoutsos

Strathclyde Institute Of Pharmacy And Biomedical Sciences

Research output: Contribution to conference › Poster

23 Downloads (Pure)

Abstract

Background: Digital design, assisted by data science, experienced significant progress over recent years within the continuous manufacturing in the pharmaceutical sector.
Research Objective: The project focuses the fundamental research on robust numerical and visual performance indicators for assessing performance for many-objective optimisation algorithms under multiple constraints
Methods: A surrogate model-based machine learning algorithm is used, to train data-driven models that capture the manufacturing process behaviour. Then use optimisation algorithms to get optimal solutions.
Results: >75% dissolution release could be achieved in 45 minutes.

Original language	English
Pages	22-22
Number of pages	1
Publication status	Published - 16 May 2022
Event	CMAC Annual Open Day 2022 - Glasgow, United Kingdom Duration: 16 May 2022 → 18 May 2022

Conference

Conference	CMAC Annual Open Day 2022
Country/Territory	United Kingdom
City	Glasgow
Period	16/05/22 → 18/05/22

Keywords

digital design
pharmaceutical manufacturing
many-objective optimisation algorithms

Access to Document

Wu-etal-CMAC-2022-Many-objective-process-optimisation-with-constraintsFinal published version, 1.61 MBLicence: Strath_1

Cite this

@conference{33648a0460084d3fb9bd7a6185cf9bad,

title = "Many-objective process optimisation with constraints for continuous tableting lines: a case study in lovastatin",

abstract = "Background: Digital design, assisted by data science, experienced significant progress over recent years within the continuous manufacturing in the pharmaceutical sector. Research Objective: The project focuses the fundamental research on robust numerical and visual performance indicators for assessing performance for many-objective optimisation algorithms under multiple constraints Methods: A surrogate model-based machine learning algorithm is used, to train data-driven models that capture the manufacturing process behaviour. Then use optimisation algorithms to get optimal solutions. Results: >75\% dissolution release could be achieved in 45 minutes.",

keywords = "digital design, pharmaceutical manufacturing, many-objective optimisation algorithms",

author = "Wu, \{Kai Eivind\} and Brown, \{Cameron J.\} and Robertson, \{Murray N.\} and Johnston, \{Blair F.\} and George Panoutsos",

year = "2022",

month = may,

day = "16",

language = "English",

pages = "22--22",

note = "CMAC Annual Open Day 2022 ; Conference date: 16-05-2022 Through 18-05-2022",

}

TY - CONF

T1 - Many-objective process optimisation with constraints for continuous tableting lines

T2 - CMAC Annual Open Day 2022

AU - Wu, Kai Eivind

AU - Brown, Cameron J.

AU - Robertson, Murray N.

AU - Johnston, Blair F.

AU - Panoutsos, George

PY - 2022/5/16

Y1 - 2022/5/16

N2 - Background: Digital design, assisted by data science, experienced significant progress over recent years within the continuous manufacturing in the pharmaceutical sector. Research Objective: The project focuses the fundamental research on robust numerical and visual performance indicators for assessing performance for many-objective optimisation algorithms under multiple constraints Methods: A surrogate model-based machine learning algorithm is used, to train data-driven models that capture the manufacturing process behaviour. Then use optimisation algorithms to get optimal solutions. Results: >75% dissolution release could be achieved in 45 minutes.

AB - Background: Digital design, assisted by data science, experienced significant progress over recent years within the continuous manufacturing in the pharmaceutical sector. Research Objective: The project focuses the fundamental research on robust numerical and visual performance indicators for assessing performance for many-objective optimisation algorithms under multiple constraints Methods: A surrogate model-based machine learning algorithm is used, to train data-driven models that capture the manufacturing process behaviour. Then use optimisation algorithms to get optimal solutions. Results: >75% dissolution release could be achieved in 45 minutes.

KW - digital design

KW - pharmaceutical manufacturing

KW - many-objective optimisation algorithms

M3 - Poster

SP - 22

EP - 22

Y2 - 16 May 2022 through 18 May 2022

ER -

Many-objective process optimisation with constraints for continuous tableting lines: a case study in lovastatin

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this