Implementation of a Modified Swarm Intelligence Algorithm in Inventory Control Practices: A Case Study

Improving inventory control is one of the main requirements for monitoring inventory practices in many industrial sectors because of its impact on process flow and productivity. An electric power transmission and distribution com-pany was chosen as a case study in this research due to the suffering...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Industrial Engineering & Management Systems Jg. 24; H. 3; S. 354 - 373
Hauptverfasser: Hamdan, Ayat Deah, Al Saffar, Iman Q.
Format: Journal Article
Sprache:Englisch
Veröffentlicht: 대한산업공학회 01.09.2025
Schlagworte:
산업공학
ISSN:1598-7248, 2234-6473
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Improving inventory control is one of the main requirements for monitoring inventory practices in many industrial sectors because of its impact on process flow and productivity. An electric power transmission and distribution com-pany was chosen as a case study in this research due to the suffering of inventory issues that the company has faced with an improper inventory control system leading to stock out and overstock of inventory items, which causes higher inventory costs. This research aims to minimize inventory costs for twenty tries (products). A classical combined model of Particle Swarm Optimization (PSO) Intelligence and an Artificial Neural Network (ANN) was implemented to create the cost objective function. Two modified algorithms of PSO for (linear inertia weight) and modified PSO for (non-linear inertia weight) were used to compare the findings with the classical PSO. The results suggest that using a modified PSO with Non-Linear Inertia Weight (NLIW) where the total cost is ($2533200) is superior to the classical PSO of the entire cost of ($11069000) and a modified PSO with Linear Inertia Weight (LIW) at a total cost of (8266400$). KCI Citation Count: 0
ISSN:1598-7248
2234-6473
DOI:10.7232/iems.2025.24.3.354