a model for process control in agile supply chain networks using artificial neural networks

Model to enhance agility in supply chain networks, focusing on optimizing decision-makingunder demand fluctuations and cost constraints.methods: a quantitative descriptive design was employed, utilizing cluster sampling (n=384)from a manufacturing company’s customer base. the ann model integrated key variables(e.g., raw material flow, production volume, storage capacity) and was tested via sensitivityanalysis to evaluate the impacts of production cost, service level, and factory capacity changeson objective function values.results: the model significantly improved supply chain agility, enabling a dynamic responseto demand shifts. a 111% production cost variation altered costs by ±15.7%, while a 91%capacity reduction rendered the model infeasible. a 411% demand surge disrupted servicelevels (91%), highlighting capacity constraints. flexibility indicators (e.g., productionadaptability) emerged as critical agility drivers.conclusion: the ann-based model optimizes supply chain performance, particularlyin healthcare contexts where responsiveness and cost efficiency are paramount. practicalrecommendations include workforce skill development, just-in-time production systems, andenhanced supplier it integration.