Artificial Intelligence Driven Process Optimization in Smart Manufacturing Systems

Abstract

The transformation toward smart manufacturing requires adaptive and data-driven process optimization to enhance industrial competitiveness. This study aims to examine the effect of Artificial Intelligence (AI) on operational efficiency, machine downtime reduction, and production quality in smart manufacturing systems. A quantitative explanatory approach with a cross-sectional survey was employed. Data were collected from 210 production managers, operational supervisors, and engineers in manufacturing companies implementing digital technologies. Respondents were selected using purposive sampling, and the data were analyzed using Structural Equation Modeling–Partial Least Squares (SEM-PLS). The findings reveal that AI has a positive and significant effect on operational efficiency (β = 0.812; t = 18.764; p < 0.001), machine downtime reduction (β = 0.746; t = 15.283; p < 0.001), and production quality (β = 0.781; t = 17.951; p < 0.001). The novelty of this study lies in simultaneously examining these three dimensions of process optimization, providing a more comprehensive perspective on AI-driven smart manufacturing.