A lean smart framework for predictive agility in manufacturing using action research

Area of Science:

• Industrial Engineering
• Operations Management
• Manufacturing Systems

Background:

• Smart technology integration in Lean Manufacturing aims for operational sustainability.
• Digital technologies often fail in unstable physical processes, creating 'digital waste'.
• A gap exists between physical process stability and digital technology integration.

Purpose of the Study:

• To propose and validate a sequential 'three tier architecture' for integrating smart technology with Lean Manufacturing.
• To establish lean physical stability as a prerequisite for cyber-physical connectivity and mathematical optimization.
• To provide a cost-effective framework for SMEs to enhance material circularity and operational reliability.

Main Methods:

• Action Research methodology was employed.
• Sequential implementation of flow-control (5S/Kanban), Internet of Things (IoT) for condition monitoring, and Mixed-Integer Linear Programming (MILP) using Python.
• Validation through empirical evidence from a manufacturing environment.

Main Results:

• The integrated approach significantly outperformed siloed implementations.
• Predictive modeling reduced wear-related waste from 28.67% to 9.07%.
• MILP optimization increased block utilization by 10.72% and reduced total process waste from 15.28% to 10.35%.

Conclusions:

• Lean physical stability is a critical moderator of 'Predictive Agility' in manufacturing.
• The proposed 'three tier architecture' offers a viable framework for Lean 4.0.
• SMEs can achieve enhanced material circularity and operational reliability cost-effectively.