Chapter 5 — full chapter
5.6 Smart and Human-Centred Manufacturing
For decades, industrial automation was synonymous with high-speed, rigid machinery engineered exclusively for mass production. Today, driven by the principles of Industry 5.0, progressive manufacturers are transitioning toward Smart and Human-Centred Manufacturing. This approach redefines the factory as a collaborative ecosystem where advanced technology enhances human craftsmanship, improves ergonomics, and boosts operational agility.
At the heart of this evolution are integrated smart factory systems that connect physical production with digital intelligence, addressing the fashion supply chain’s longstanding issues: fragmented workflows, long lead times, and high defect rates. These systems require reskilling and upskilling to transform the workforce from operators to coordinators.
This modern manufacturing framework is driven by a combination of enabling technologies: IoT, AI, and computer vision.
Internet of Things (IoT) sensors are embedded directly into industrial sewing and processing equipment. These devices monitor key variables and assess operator ergonomics. The real-time data is collected by centralized artificial intelligence platforms, which utilize predictive analytics to identify operational bottlenecks, forecast equipment degradation before mechanical failure occurs, and dynamically adjust workflows to reduce physical strain on personnel.
The most effective applications of these technologies are in monitoring and quality control. Traditionally, apparel quality assurance relied on reactive, post-production visual inspections, an inefficient process susceptible to human fatigue and often resulting in late defect detection.
By utilizing computer vision, high-resolution sensors continuously scan textiles during cutting and sewing processes, with machine learning models identifying anomalies such as warping, dropped stitches, or pattern misalignments in real time.
It functions as a decision-support tool, alerting operators via augmented reality or digital displays to precisely locate defects, thereby enabling immediate correction. This approach helps reduce textile waste and eases the cognitive workload on workers.
However, transitioning to this human-centric paradigm presents substantial systemic challenges. The primary barriers to widespread adoption are the high initial costs for setting up IoT infrastructure, a real shortage of workers trained to handle AI-based systems, and the fragmented nature of the industry. Furthermore, integrating old-school machinery with modern digital twins often introduces technical friction, while brands must carefully navigate data privacy concerns regarding the monitoring of operator ergonomics. Overcoming these economic and structural hurdles will determine whether the industry can successfully scale these technologies to realize a truly resilient, smart and human-centered future for apparel manufacturing.