AI-Supported Process Management Tools for Handling Disturbances in Industry 4.0 Production Systems

Abstract

Production systems operating in Industry 4.0 environments are increasingly exposed to disturbances that affect process stability, performance, and managerial decision-making. The growing complexity and digital integration of production processes require structured approaches that go beyond reactive disturbance handling and support process-oriented management. In this context, artificial intelligence (AI) is increasingly used as a decision-support mechanism to enhance data interpretation and managerial responses. This article aims to examine how AI-supported process management tools can be used to handle disturbances in Industry 4.0 production systems. A structured qualitative coding methodology is proposed and applied to systematically identify disturbances, corresponding management actions, and disturbance-related process signals. Disturbances are classified using D-codes, management responses using A-codes, and observable indicators using signal codes, forming an integrated analytical framework for process-level analysis. Empirical data collected from real production systems were analyzed using the proposed coding approach. AI-supported data processing was used to assist pattern recognition, signal interpretation, and the linking of disturbances with management actions, without replacing human judgment in decision-making. The results provide an empirically grounded classification of disturbances and process management tools relevant to digitally integrated production environments. The study contributes to production engineering and management literature by offering a transferable methodological framework for analyzing disturbance handling in Industry 4.0 production systems. From a practical perspective, the findings demonstrate how basic process management tools, supported by AI-based decision-support, can enhance managers’ ability to identify, interpret, and respond to disturbances in complex production processes.