Jul 2026· 2026 International Conference on Intelligent and Sustainable AI Systems (ICOSAAS)· pp. 198-204· 0 citations· 14 references
Abstract
Industrial machinery operating in manufacturing and process environments is frequently subjected to adverse operating conditions such as excessive temperature rise, abnormal current consumption, and mechanical vibrations, which may lead to performance degradation, unexpected failures, production losses, and safety hazards. To address these challenges, this paper presents the design and implementation of an Internet of Things (IoT)-enabled real-time machine health monitoring and protection system based on the ESP32 microcontroller platform. The proposed system integrates a DHT11 sensor for temperature and humidity monitoring, an ACS712 Hall-effect sensor for current measurement, and an MPU9250 inertial measurement unit (IMU) for vibration analysis. Sensor data are continuously acquired, processed, and transmitted through Wi-Fi to a cloud-based Firebase Realtime Database, enabling remote access and centralized monitoring. A responsive web dashboard hosted on GitHub Pages provides real-time visualization of machine operating parameters, status indicators, and fault notifications. To enhance operational safety and equipment reliability, threshold-based fault detection algorithms are implemented to identify abnormal operating conditions. When predefined critical limits are exceeded, the ESP32 automatically initiates protective actions by disconnecting the machine through a relay module, activating a visual alarm, and updating the fault status on the cloud platform. The dashboard additionally supports bidirectional communication, allowing authorized operators to remotely restart the machine, while a local push-button interface enables manual system recovery. Furthermore, the developed platform incorporates a browser-based logging mechanism that records timestamped sensor measurements, machine status transitions, fault events, and downloadable CSV trend data for maintenance analysis and performance evaluation. Experimental validation demonstrates reliable real-time monitoring with a data refresh interval of approximately 3 s, accurate threshold-based fault detection, dependable cloud connectivity, and effective remote supervisory control. The proposed solution offers a low-cost, scalable, and practical framework for predictive maintenance and industrial equipment condition monitoring in smart manufacturing environments.
Industry 4.0 has accelerated the adoption of Internet of Things (IoT) technologies for intelligent industrial automation, enabling continuous monitoring of critical environmental and operational parameters. This paper presents an IoT-based Industrial Parameters Monitoring System developed using the STM32F446RE microcontroller for real-time monitoring of industrial conditions. The proposed system integrates multiple sensors, including the MQ135 gas sensor, BMP280 pressure and temperature sensor, DHT11 humidity sensor, KY-026 flame sensor, and SW-420 vibration sensor, to collect and process data related to industrial safety and environmental conditions. Sensor data are acquired through ADC, GPIO, and I²C interfaces and displayed locally on a 16×2 LCD. A WE10 Wi-Fi module enables wireless transmission of processed data to the Right Tech Cloud platform through UART communication, facilitating remote monitoring and visualization. The system also incorporates an audible alert mechanism using a buzzer to notify users when abnormal conditions such as gas leakage, fire, or excessive vibration are detected. Experimental evaluation demonstrates reliable real-time data acquisition, cloud connectivity, and continuous monitoring performance. The proposed solution provides a low-cost, scalable, and efficient approach for improving industrial safety, minimizing manual intervention, and supporting predictive monitoring applications in smart manufacturing environments.
Manasa Yerramsetti, Ganesh Gantyada, Divya Matam et al.· International Journal of Sci...· 0 citations
The emergence of Internet of Things (IoT) has undoubtedly transformed safety, automation, and monitoring systems across various sectors, particularly in smart home environments. This study presents the design and implementation of an Internet of Things (IoT)-based real-time kitchen monitoring and automation system aimed at enhancing safety, efficiency, and intelligent control within kitchen environments. The system was developed to address the limitations of manual monitoring processes, which are often labor-intensive, error-prone, and unreliable in emergency situations. The system integrates multiple sensors to enable real-time alerts and automated responses. Wireless communication is achieved through a Wi-Fi network connected to the Blynk IoT platform, allowing remote monitoring via smartphones and laptops. Upon detection of hazardous conditions such as gas leakage, fire outbreak, abnormal temperature levels, motion intrusion, or low water levels, the system triggers local alarms and transmits notifications to users through the IoT dashboard. Sensor fusion techniques were applied to enhance data accuracy and reduce false alarms. Experimental evaluation was conducted under simulated real-world kitchen scenarios to assess responsiveness, accuracy, and reliability. The results demonstrated an overall system accuracy of 91.8%, with high detection reliability across all integrated sensors and minimal false positives.
Simon Usiju Chagwa, P. B. Zirra· Journal of Analytical and Ap...· 0 citations
Conventional electricity metering systems are limited by their inability to provide real-time monitoring, remote access, and accurate information on energy consumption, which in turn reduces the efficiency of energy management and billing processes. This study aimed to design and implement an Internet of Things (IoT)-based smart energy meter capable of real-time monitoring and MATLAB-based data analytics. A prototype development methodology was adopted, using an ESP32 microcontroller integrated with ACS712 current and ZMPT101B voltage sensors, an LCD module, Wi-Fi communication, and the Blynk cloud platform. Electrical parameters were measured under varying load conditions and transmitted wirelessly for remote monitoring, while MATLAB was used to analyse and visualise the collected data. The developed system successfully measured voltage, current, power, and energy consumption, with recorded values of approximately 220 V, 0.40–1.20 A, 88–264 W, and 0.088–0.264 kWh, respectively. The graphical outputs clearly illustrated voltage stability, load variation, instantaneous power consumption, and cumulative energy usage, thereby improving users’ ability to monitor electrical energy in real time. Although slight measurement deviations caused by sensor calibration, signal noise, and network dependence were observed, the system demonstrated reliable performance throughout the testing period. The findings indicate that integrating IoT technology with cloud communication and MATLAB analytics provides a practical, low-cost, and scalable solution for intelligent energy monitoring. The study concludes that the proposed system offers significant improvements over conventional metering systems by enabling continuous monitoring, remote access, and informed energy management. Future work should focus on improving sensor calibration, incorporating artificial intelligence for predictive energy analysis, supporting three-phase installations, and providing offline data storage to further enhance system reliability and scalability.
DANJUMA, I. M., ASIH, M., GARBA, S. S. et al.· International Journal of App...· 0 citations
The increasing demand for renewable energy has highlighted the need for efficient and reliable management of solar power plants. Solar plants, whether residential or industrial, require continuous monitoring to ensure optimal performance, detect faults, and maximize energy generation. Manual supervision is often time-consuming, prone to errors, and insufficient for detecting real-time anomalies. To address these challenges, this paper presents an IoT-based Solar Plant Monitoring System that enables remote, real-time observation and management of solar energy systems. The proposed system integrates sensors, microcontrollers, and IoT-enabled communication modules to collect key parameters such as solar panel voltage, current, temperature, and battery status. These parameters are transmitted over the internet to a centralized cloud platform, allowing plant operators to monitor system performance from any location using smartphones, laptops, or tablets. Alerts are generated automatically in case of abnormal readings, such as low voltage, panel overheating, or battery faults, facilitating proactive maintenance and minimizing downtime. By leveraging IoT technology, the system not only improves the efficiency and reliability of solar power generation but also reduces operational and maintenance costs. The proposed system supports data logging, historical analysis, and performance optimization. Additionally, the integration of cloud-based monitoring ensures scalability and flexibility, allowing expansion to multiple solar plants and large-scale installations.
S. S., A. S, D. K. et al.· International Conference Com...· 0 citations
Introduction: Methane and toxic gases build up in sewer pipes and septic tanks and are extremely dangerous in their ability to cause explosions and poisoning to workers in the confined sewer. The traditional monitoring controls, like infection ventilation and human checking, cannot be used to offer real-time protection.
Methods: In this work, the authors show an Internet of Things (IoT)-enabled cyber-physical system of real-time gas detection and automated mitigation. The system combines the MQ-4 (methane), MQ-135 (CO2 /NH 3/VOCs), and MQ-136 (H2S) sensors and place on the ESP32 microcontroller. A moving average-based compensation method is used to stabilize a sensor in contaminated conditions with minimum recalibration requirements. Alerts and ventilation are activated when methane reaches over 25% of the Lower Explosive Limit (LEL) using MQTT, in accordance with OSHA and NFPA safety requirements.
Results: Testing with 250 cases indicated that the system is reliably able to detect hazards, alert, and mitigate without failure. The response time was 8.2 seconds on average, which is a safeguard against gas buildup. Multi-gas sensitivity (±18% was within a reasonable range, and the system was able to run on backup power up to 18 hours.
Conclusion: The offered IoT system would turn the sanitation safety from passive observation to active protection due to real-time multi-gas detection and automated response. It offers an affordable yet scalable way of ensuring occupational safety within dangerous confined spaces.
Ramu Penki, Boddu Jagadeesh, S Arun Kumar et al.· International Journal of Occ...· 0 citations
This study aimed to (1) design and develop an IoT-based hardware system for real-time air pollution monitoring, (2) develop an interactive mobile application for reporting and alert notifications, and (3) evaluate the system’s spatial stability and data transmission performance. The proposed framework integrates Internet of Things (IoT) technology with cloud-based database architecture. The sensing node incorporates a SEN55 environmental sensor and an ESP32 microcontroller to collect key parameters, including PM2.5, VOC Index, and NOx Index. Sensor readings are processed using an edge aggregation algorithm to reduce signal noise before being stored in Firebase Realtime Database for real-time synchronization with the “React AQI” mobile application, developed using the React Native framework. The application supports multilingual visualization in Thai, English, and Chinese. Experimental results demonstrated a high average Data Delivery Ratio (DDR) of 94.76%, with data reliability ranging between 95.7% and 97.5%. A 20-day spatial comparative deployment conducted at Building 22 and Building 26 revealed consistent differentiation in pollution levels across locations, with a mean PM2.5 difference of 1.54 µg/m3. The system effectively visualized pollution trends through interactive graphical analytics. These findings indicate that the proposed framework serves as an innovative prototype for Smart Health management within higher education institutions, aligned with the global Smart Campus paradigm.
S. Janpla, Thanakorn Uiphanit· International Journal of Int...· 0 citations
