In this paper, a system for measuring the zone temperature profile of a horizontal tube furnace is proposed. This system consists of an ultrasonic transducer, quartz tube, resistive horizontal tube furnace, Arduino micro-controller and relevance vector machine (RVM) based regression model. The ultrasonic transducer is placed in such a way that the acoustic wave is transmitted and then reflected back from the resistive horizontal tube furnace. The variations in the temperature values inside the tube furnace may affect the receiving voltage of the ultrasonic transducer. The RVM model is employed to predict the temperature using the inputs as the ultrasonic transducer voltage and the distance of the propagating path of the ultrasonic wave. The experimental results demonstrate that the proposed system is effective to measure the temperature inside a horizontal furnace and it shows a correlation coefficient value of 0.9695 with the K-type thermocouple readings. Such a system can be employed in an industrial furnace to measure the temperature with a higher accuracy.

Industrial equipment failures lead to costly downtime and maintenance inefficiencies. This research presents a real-time predictive maintenance system leveraging IoT sensors and machine learning (ML) models for automated fault detection and performance optimization. The system integrates IoT-based sensors, real-time data analytics, and ML algorithms to monitor industrial equipment, predict failures, and optimize maintenance processes. Sensors collect real-time operational data from industry, which is securely transmitted using efficient protocols and stored for further analysis. Advanced ML algorithms analyze this data to detect patterns indicative of equipment failures, providing predictive insights to enhance reliability. A web-based interface enables employees to monitor equipment status, receive maintenance recommendations, and request actions, ensuring precision in data handling while reducing manual errors. The study highlights the system’s potential to improve accuracy, reduce maintenance costs, and increase operational efficiency by minimizing downtime and enhancing reliability.