Production Optimization and Integrated Planning in the Textile Industry: A Concise Critical Review

Authors

Abstract

The textile industry faces a fundamental challenge: optimizing cost, speed, quality, and sustainability simultaneously. While artificial intelligence (AI) and advanced technologies offer transformative potential in predictive maintenance, defect detection, and resource optimization, significant adoption barriers persist. Key limitations include poor scalability of lab-developed AI models to real production environments, data scarcity among SMEs, and economic conflicts between sustainable practices and fast-fashion demands. Despite achieving 85-95% accuracy in controlled settings, less than 15% of manufacturers have successfully implemented AI solutions at scale. Digital twins and predictive analytics show promise but face high adoption costs and workforce resistance. Similarly, sustainable materials struggle with 20-50% higher costs and slower processing speeds. This review highlights the critical need to shift research focus from theoretical advances to practical deploy-ability. Emerging solutions like federated learning and Blockchain traceability offer pathways forward, but success requires hybrid human-AI systems that balance automation with workforce adaptability. The future of textile manufacturing depends on bridging the innovation-adoption gap through collaborative efforts prioritizing scale-able and economically viable solutions.

Downloads

Published

2025-12-05

Issue

Section

Peer Reviewed Article