This research presents a sensor-based IoT system using ESP32 to enhance efficiency in apparel manufacturing. By integrating touch, IR, vibration, and current sensors, it captures real-time operator cycle time and machine runtime. The system identifies bottlenecks, predicts anomalies, and reduces downtime through machine learning analysis. It automates performance tracking, highlights skill gaps, and supports predictive maintenance. Data is visualized via a dashboard, enabling informed decision-making and streamlined production. Compared to existing tools like Thulita and Andon, this solution offers accurate, real-time insights, improving productivity and reducing machine repair costs in live production environments.
“I’m truly grateful for the chance to present in the Engineering, Technological Science, and Innovation category. I feel a lot of pleasure to do my best and aim for the Best Presenter Award. This opportunity means so much to me and will be a big step forward in building my future career. Thank you again for this opportunity.”