Browsing by Author "Sani, Shehu"

Now showing 1 - 3 of 3
  • Thumbnail Image
    ItemOpen Access
    Supply chain 4.0 and the digital twin approach: a framework for improving supply chain visibility
    (Elsevier, 2024-10-15) Sani, Shehu; Zarifnia, Alireza; Salonitis, Konstantinos; Milisavljevic-Syed, Jelena
    The emergence of Industry 4.0 has led to an increased level of complexity in supply chain operations. As a result, innovative approaches are required to improve visibility. Conventional approaches such as optimisation and simulation are no longer adequate for ensuring visibility across the entire supply chain. The aim of this study is to explore the potential of digital twins (DT) within the domain of supply chain management. A comprehensive DT framework is formulated utilising the Genetic Algorithm (GA). The results emphasise the potential of DT in promoting data-driven decision-making, improving visibility, and optimising SC operations. This study attempts to fill the current gaps in knowledge, offering significant insights for stakeholders in the supply chain.
  • Thumbnail Image
    ItemOpen Access
    Supply chain 4.0: a machine learning-based Bayesian-optimized lightGBM model for predicting supply chain risk
    (MDPI, 2023-09-04) Sani, Shehu; Xia, Hanbing; Milisavljevic-Syed, Jelena; Salonitis, Konstantinos
    In today’s intricate and dynamic world, Supply Chain Management (SCM) is encountering escalating difficulties in relation to aspects such as disruptions, globalisation and complexity, and demand volatility. Consequently, companies are turning to data-driven technologies such as machine learning to overcome these challenges. Traditional approaches to SCM lack the ability to predict risks accurately due to their computational complexity. In the present research, a hybrid Bayesian-optimized Light Gradient-Boosting Machine (LightGBM) model, which accurately forecasts backorder risk within SCM, has been developed. The methodology employed encompasses the creation of a mathematical classification model and utilises diverse machine learning algorithms to predict the risks associated with backorders in a supply chain. The proposed LightGBM model outperforms other methods and offers computational efficiency, making it a valuable tool for risk prediction in supply chain management.
  • Thumbnail Image
    ItemOpen Access
    Towards pre-emptive resilience in military supply chains: a compromise decision support model-based approach
    (Taylor & Francis, 2023-06-09) Sani, Shehu; Schaefer, Dirk; Milisavljevic-Syed, Jelena
    The complex and dynamic nature of military supply chains (MSC) requires constant vigilance to sense potential vulnerabilities. Several studies have employed decision support models for the optimization of their operations. These models are often limited to a best single-point solution unsuitable for complex MSC constellations. In this article, the authors present a novel approach based on decision support models to explore a range of satisficing solutions against disruptions in MSCs using a compromise Decision Support Problem (cDSP) construct and Decision Support in the Design of Engineered Systems (DSIDES). Two cases were evaluated: (1) a baseline scenario with no disruption and (2) with disruption to achieve target values of three goals: (1) minimizing lead time, (2) maximizing demand fulfilment and (3) maximizing vehicle utilization. The results obtained in Case 1 identified a more stable solution space with minimal deviations from the target value, while in Case 2 the solution space was unstable with deviations from the target values.