A Machine Learning-Based Framework for Sustainable Transition from Industry 4.0 to Industry 5.0 in Indian Manufacturing

Abstract

The transition from Industry 4.0 to Industry 5.0 marks a critical shift toward human-centric, resilient, and sustainable manufacturing. Indian industries, despite increasing adoption of Industry 4.0 technologies, continue to face challenges related to digital maturity, workforce adaptability, and sustainability integration. This study proposes a machine-learning-driven framework to evaluate and enhance the sustainability of Industry 4.0 technologies and to support a structured transition towards Industry 5.0. Empirical data were collected from sixteen Indian manufacturing firms using a structured survey and expert interviews. Technologies were evaluated based on maturity, importance, human adaptability, cost index, and energy efficiency. Correlation analysis revealed that smart sensors (r = 0.824) and robotic arms (r = 0.877) demonstrated the highest sustainability levels, whereas big-data analytics (r = 0.35) and cyber-physical systems (r = 0.56) faced constraints due to cost, infrastructure, and skill gaps. A supervised machine-learning model achieved R² = 0.86 for predicting sustainability scores and highlighted human adaptability and maturity as the dominant predictors. The DEMATEL analysis further identified social risks as the most influential enablers affecting the digital transition. The findings establish that human-centric readiness, structured digital strategies, and targeted training are essential for India’s progression to Industry 5.0. The proposed ML-based framework provides a decision-support system for policymakers and industries aiming to achieve sustainable, human-centric, and resilient manufacturing ecosystems.