Abstract
{ "background": "Manufacturing systems in developing economies face unique operational risks, yet methodological frameworks for their comparative evaluation are often inadequate. Existing risk assessment models frequently lack the capacity to integrate multi-level data and quantify uncertainty in a principled manner.", "purpose and objectives": "This study aims to develop and apply a novel Bayesian hierarchical model for the comparative methodological evaluation of manufacturing plant systems, with the objective of quantifying risk reduction and identifying dominant failure pathways.", "methodology": "A comparative study was conducted across multiple manufacturing plants. The core methodological innovation is a Bayesian hierarchical model, $y{ij} \\sim \\text{Normal}(\\alphaj + \\beta X{ij}, \\sigma^2), \\; \\alphaj \\sim \\text{Normal}(\\mu{\\alpha}, \\tau^2)$, which pools information across plants to estimate plant-specific risk parameters $\\alphaj$ and shared covariate effects $\\beta$. Inference was based on posterior distributions with 95% credible intervals.", "findings": "The model identified systemic electrical faults as the predominant risk contributor, accounting for an estimated 38% of total operational downtime. Posterior estimates revealed that plants implementing predictive maintenance protocols had a mean reduction in critical failure risk of 24.7% (95% CrI: 18.1, 31.2).", "conclusion": "The Bayesian hierarchical framework provides a robust methodological tool for comparative risk analysis, offering superior uncertainty quantification over conventional methods. It effectively identifies common and plant-specific risk factors within the studied manufacturing context.", "recommendations": "Manufacturing operations should adopt hierarchical modelling approaches for plant system evaluation. Regulatory and support frameworks should encourage the collection of standardised, multi-level operational data to facilitate such analyses.", "key words": "Bayesian hierarchical model, risk assessment, manufacturing systems, comparative study, operational reliability", "contribution statement": "This paper introduces a novel application of Bayesian hierarchical modelling for the comparative evaluation of manufacturing systems, providing a methodological framework that explicitly quantifies