Table 1 Comparison of traditional and... | Emerald Publishing

Table 1

Comparison of traditional and intelligent MES

Characteristic	Traditional MES	Intelligent MES
Main objective	Simplify production execution and link planning (ERP) with control systems (PLC, sensors)	Maximize production data for continuous improvement and optimization with BDA
Data management	Collect and store production data, primarily used for performance indicator calculation	Real-time management and analysis of massive, diverse data from various sources using BDA to extract insights
Analysis and decision	Performance indicator calculation (such as OEE) with limited diagnostic support, relying on human expertise	Real-time visibility and performance analysis with advanced diagnostic support, enabling fast and intelligent decision making at all levels
Intelligence and autonomy	Reactive and rule-based, relying on human expertise	Autonomous and intelligent operations with AI and ML for maintenance, detection, optimization, and decision making
Integration	Interoperability through integration with ERP, PLM (Product Lifecycle Management), and traceability systems, following the ISA-95 standard	Fast and secure integration with a broad ecosystem of systems and devices, enabling vertical integration within Industry 4.0
Diagnosis	Limited and predefined failure diagnosis with minimal analysis of performance and quality issues	Advanced diagnostic capabilities using probabilistic models to identify performance deviation causes
Reactivity	Reactivity based on configured information and alerts	Real-time responsiveness through continuous data analysis

Characteristic	Traditional MES	Intelligent MES
Main objective	Simplify production execution and link planning (ERP) with control systems (PLC, sensors)	Maximize production data for continuous improvement and optimization with BDA
Data management	Collect and store production data, primarily used for performance indicator calculation	Real-time management and analysis of massive, diverse data from various sources using BDA to extract insights
Analysis and decision	Performance indicator calculation (such as OEE) with limited diagnostic support, relying on human expertise	Real-time visibility and performance analysis with advanced diagnostic support, enabling fast and intelligent decision making at all levels
Intelligence and autonomy	Reactive and rule-based, relying on human expertise	Autonomous and intelligent operations with AI and ML for maintenance, detection, optimization, and decision making
Integration	Interoperability through integration with ERP, PLM (Product Lifecycle Management), and traceability systems, following the ISA-95 standard	Fast and secure integration with a broad ecosystem of systems and devices, enabling vertical integration within Industry 4.0
Diagnosis	Limited and predefined failure diagnosis with minimal analysis of performance and quality issues	Advanced diagnostic capabilities using probabilistic models to identify performance deviation causes
Reactivity	Reactivity based on configured information and alerts	Real-time responsiveness through continuous data analysis

Source(s): Authors’ own work