Intelligent Factory Safety and Emergency Response System Using LabVIEW

Abstract

The main goal of this study is to develop an intelligent factory safety and emergency response system using IoT, Machine Learning, and LabVIEW ensuring industrial safety requires continuous monitoring of critical parameters such as vibration, temperature, humidity, and sound. Manual monitoring is inefficient and prone to errors. This system employs real-time sensor data acquisition, anomaly detection using machine learning, and trend analysis for predictive maintenance. Sensor data is logged into Firebase and Google Sheet, training the ML model using the data from the google sheets, enabling visualization in LabVIEW. The system analyzes the past 5 minutes, current sensor data, and forecasts the next 5 minutes to ensure timely prediction. In addition to visualization, the system includes an automated alert mechanism that sends SMS notifications to designated personnel whenever an anomaly is detected, ensuring immediate response to potential hazards. Safety mechanisms such as relay-based emergency shutdowns can be triggered automatically to prevent catastrophic failures. By integrating real-time anomaly detection, predictive maintenance, and automated emergency response, this system enhances industrial safety, improves operational efficiency, and minimizes unplanned downtime. The proposed approach ensures a proactive, data-driven strategy for factory safety management, reducing risks and optimizing industrial processes.