<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>Drug quality problems caused by problems in drug production processes generally cannot be effectively controlled by current drug quality standards, leading to potential safety risks for drugs. This paper applies the information system to promote the command and control of drug production to the quality control of the drug production process. By using five key quality technology points affecting drug quality as the input of the improved PSO-BP algorithm for network training based on the GMP (Good Manufacturing Practice) standard, the output of the classification prediction network is used to determine whether the drug is qualified or not to achieve the purpose of drug quality control. The parameters of the BP algorithm are optimized to minimize the output error after the PSO algorithm is improved by invoking the linear variational operator. The results show that the average absolute error and the average relative error of the improved PSOBP algorithm are 0.129 and 1.86%, respectively, and the average absolute error and the average relative error of the PSOBP algorithm are 0.694 and 8.28%, respectively, compared with the PSO-BP algorithm, the error of the improved PSOBP algorithm is effectively reduced. The improved PSO-BP algorithm proposed in this paper can be used for drug production command supervision, and it effectively reduces the inferiority rate of drug production and fundamentally eliminates the circulation market of inferior drugs.</p>
</abstract>

Drug quality problems caused by problems in drug production processes generally cannot be effectively controlled by current drug quality standards, leading to potential safety risks for drugs. This paper applies the information system to promote the command and control of drug production to the quality control of the drug production process. By using five key quality technology points affecting drug quality as the input of the improved PSO-BP algorithm for network training based on the GMP (Good Manufacturing Practice) standard, the output of the classification prediction network is used to determine whether the drug is qualified or not to achieve the purpose of drug quality control. The parameters of the BP algorithm are optimized to minimize the output error after the PSO algorithm is improved by invoking the linear variational operator. The results show that the average absolute error and the average relative error of the improved PSOBP algorithm are 0.129 and 1.86%, respectively, and the average absolute error and the average relative error of the PSOBP algorithm are 0.694 and 8.28%, respectively, compared with the PSO-BP algorithm, the error of the improved PSOBP algorithm is effectively reduced. The improved PSO-BP algorithm proposed in this paper can be used for drug production command supervision, and it effectively reduces the inferiority rate of drug production and fundamentally eliminates the circulation market of inferior drugs.

Information technology system to promote drug production command supervision

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution 4.0 International License.

{"article-title":"Information technology system to promote drug production command supervision"}

Drug quality problems caused by problems in drug production processes generally cannot be effectively controlled by current drug quality standards, leading to...

Information technology system to promote drug production command supervision

Online veröffentlicht: 16. Aug. 2023

Seitenbereich: -

Eingereicht: 26. Okt. 2022

Akzeptiert: 24. Feb. 2023

DOI: https://doi.org/10.2478/amns.2023.2.00195

Schlüsselwörter
Drug manufacturing, Linear variational operator, Quality control, GMP, improved PSO-BP algorithm

© 2023 Jing Zhou, published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Information technology system to promote drug production command supervision

Online veröffentlicht: 16. Aug. 2023

Seitenbereich: -

Eingereicht: 26. Okt. 2022

Akzeptiert: 24. Feb. 2023

DOI: https://doi.org/10.2478/amns.2023.2.00195

SchlüsselwörterDrug manufacturing, Linear variational operator, Quality control, GMP, improved PSO-BP algorithm

© 2023 Jing Zhou, published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Schlüsselwörter
Drug manufacturing, Linear variational operator, Quality control, GMP, improved PSO-BP algorithm