When swarm meets fuzzy logic: Batch optimisation for the production of pharmaceuticals
The concept of right-first-time production is an essential feature for a successful product development process and for companies to be competitive and profitable. However, achieving such a concept is a tricky exercise across a wide spectrum of industrial domains includes the pharmaceutical industry...
Gespeichert in:
Veröffentlicht in: | Powder technology 2021-02, Vol.379, p.174-183 |
---|---|
Hauptverfasser: | , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | The concept of right-first-time production is an essential feature for a successful product development process and for companies to be competitive and profitable. However, achieving such a concept is a tricky exercise across a wide spectrum of industrial domains includes the pharmaceutical industry where granulation and tableting processes are considered to be the most critical operations in the production line. Therefore, this research paper presents a new approach that integrates a particle swarm optimization algorithm with a fuzzy logic system in order to implement a new framework by which right-first-time production of granules and tablets is ascertained systematically. The proposed approach consists of inverting the models that were previously developed. Through this control technique, one can identify the optimal operating conditions to produce the required granules and tablets, and can minimize the waste and recycling ratios. All frameworks have been successfully validated via real laboratory-scale experiments that include measurement tolerances.
[Display omitted]
•A Right-first-time model is developed for the granulation and tabletting processes.•A framework integrating particle swarm optimization with fuzzy logic is proposed.•The proposed framework is validated via a series of laboratory scale experiments.•The granules and tablets are produced right-first-time. |
---|---|
ISSN: | 0032-5910 1873-328X |
DOI: | 10.1016/j.powtec.2020.10.066 |