Jul 2026· International Conference on Advanced Optoelectronic Measurement Technology and Instruments· Vol 14269, pp. 142690T - 142690T-6· 0 citations· 9 references
Engineering
TL;DR
An intelligent monitoring system for the contact temperature of medium-voltage switch cabinets based on ZigBee technology and AI anomaly prediction, in which a lightweight AI temperature anomaly prediction model is embedded.
Abstract
In power systems, failures of medium-voltage switchgear contacts caused by high temperatures occur from time to time. Traditional temperature measurement methods are applied in enclosed and strong electromagnetic interference environments, which have certain limitations. This paper designs an intelligent monitoring system for the contact temperature of medium-voltage switch cabinets based on ZigBee technology and AI anomaly prediction. The system uses the CC2530 as its main control chip, adopts the DS18B20 digital temperature sensor to collect contact temperatures, and solves the problem of difficult power supply at the high-voltage end through a CT self-powered and battery switching solution. Based on the Z-Stack protocol stack, it realizes node networking and data transmission. Finally, LabVIEW is used to develop a host computer monitoring platform, in which a lightweight AI temperature anomaly prediction model is embedded. This model uses historical temperature data of switchgear contacts to train the Gradient Boosting Decision Tree (GBDT) algorithm, and can real-time predict potential sudden temperature rises within 5-10 minutes.
Three-phase induction motors are extensively utilized in industrial and commercial applications due to their robustness, efficiency, and capability to handle high-power loads. However, these motors are vulnerable to damage from phase failure conditions, including single-phasing, voltage imbalance, and phase loss, which can lead to overheating, reduced efficiency, and permanent equipment failure. This paper presents the design and development of a low-cost, intelligent three-phase monitoring and protection system integrated with Internet of Things (IoT) communication for real-time fault notification. The proposed system employs an Arduino Uno microcontroller as the central processing unit, continuously monitoring the availability of R, Y, and B phases through voltage sensor modules. Upon detection of any phase failure, the system automatically disconnects relay-controlled loads to prevent single-phasing damage. Local status indication is provided through an I2C LCD display and audible buzzer alerts, while remote monitoring is achieved via an ESP32 DevKit module that transmits fault notifications to a Telegram application through Wi-Fi connectivity. The system architecture combines embedded control, automated protection, and wireless communication into a single scalable platform. Experimental validation demonstrates reliable phase detection, rapid relay response, and effective remote alerting, confirming the system's suitability for industrial automation, motor protection, and smart energy management applications.
J. Babu, More Divya, Varu Chirag et al.· International Journal for Sc...· 0 citations
To ensure reliable operation of the distribution system, feeder faults, transformer stress and abnormal operating conditions need to be detected in a timely fashion. This paper proposes an edge-intelligent monitoring and real-time communication system for a three-phase 11 kV/415/230 V power distribution system, which is based on IoT. The proposed system combines the sensing of the voltage, current, active power and the LT-side and transformer-side temperature sensors with local decision logic based on thresholds and remote communication through a dedicated mobile phone and control-room interface. A mathematical model was derived to explain the following: phase voltage, phase current, power utilization, voltage deviation, overcurrent, imbalance and temperature state. The system was tested using scenarios in MATLAB/Simulink representing various operating conditions such as overloading, undervoltage, overvoltage, overheating, line-fault and normal operating conditions. The simulation results showed that the monitoring logic maintained a normal state correctly without triggering false alarms, generated alarm at warning stage when progressive overload occurred, triggered alarm at undervoltage and over-voltage at 8.0 s, and generated the alarm in the line-fault state when the voltage collapsed in combination with current surge, and triggered the alarm at warning state during the overheating simulation. Under the line fault condition, the maximum current was increased to 203.43A as compared with 94.48A under normal condition, and the overheating condition reached 98.34 °C. The results show that the integration of electrical and thermal monitoring with edge-level decision logic leads to a better situation awareness and quicker operator response. The proposed framework provides a scalable smart distribution monitoring platform and a future enhancement path towards implementation with hardware, event logging, fault-location techniques and machine-learning based fault classification.
Unknown authors· Journal of Global Social Tra...· 0 citations
The server room at the Class I Climatology Station of East Java requires reliable monitoring of temperature, humidity, flame detection, and electrical voltage; however, monitoring is still conducted manually without automatic electrical protection. This study aims to design and implement an Internet of Things (IoT)-based environmental condition monitoring and automatic electrical protection system using an ESP32 integrated with BME280, KY-026, and ZMPT101B sensors. The system applies a two-level threshold structure—warning and critical—to trigger notifications as well as automatic power disconnection via relays. The research methodology includes system design, sensor calibration of the BME280 and ZMPT101B using a comparative method, functional testing of the KY-026, and a 14-day field test. The test results demonstrated a temperature correction of -0.21 °C, a humidity correction of -0.80% RH, and an average voltage error of 1.05%. The system recorded two warning-status readings for humidity without reaching critical conditions and successfully transmitted and stored 114,903 data points during the testing period. The reading interval was designed to be 5 seconds, whereas the actual transmission interval was influenced by network conditions. The results indicate that the system can effectively support environmental monitoring and automatic electrical protection for server rooms.
Unknown authors· Internet of Things and Artif...· 0 citations
The Sudden equipment failures are common in industrial systems, which means more downtime and higher maintenance costs. A Smart AI-Integrated Predictive Maintenance and Condition Monitoring System is proposed to solve this problem. It will allow for real-time monitoring and early fault detection in industrial machines. The system uses an Arduino Uno (ATmega328P) microcontroller that is connected to several sensors, such as voltage, current, temperature (LM35), vibration, proximity, and MPU6050 sensors, to collect important operational data. The ESP8266 NodeMCU Wi-Fi module sends the processed data to an IoT cloud platform so that it can be monitored and analyzed from afar. There is also an I2C display developed in for real-time viewing on position. The proposed system uses AI-based analysis to find problems and assume when equipment might break down, which enables maintenance be performed on time. By using a hardware prototype to evaluate shows that the system reliably monitor in real time and make accurate predictions, which cuts down on downtime and makes the system work better. The Integration of AI and IoT technologies makes predictive maintenance in modern industrial settings cheaper, more flexible, and smarter.
V. R. Kumar, P. Poornima, M. Abinesh et al.· International Conference on...· 0 citations
The reliability of electrical systems plays a crucial role in ensuring the continuous operation of equipment and preventing potential damage and fires caused by electrical faults. This study aims to design and implement a web-based electrical fault monitoring and warning system using the Internet of Things (IoT) concept. The system was developed using an ESP32 microcontroller integrated with a PZEM-004T sensor, a DHT22 sensor, and an MQ-2 sensor. The measurement data is processed in real time, stored on an SD card and in a local database, and then displayed via a web interface in numerical and graphical formats. Test results showed an average error of 0.52% for voltage and 0.92% for current in the PZEM-004T sensor; calibration of the DHT22 yielded a correction of 0.074°C; and the MQ-2 sensor set the smoke detection threshold at 40 PPM. The system successfully detected abnormal voltage conditions, overcurrent or undercurrent, high temperatures, and the presence of smoke, and automatically activated the relay to cut off the power supply. The designed system successfully improved installation safety and reduced the risk of equipment damage and fire. .
Unknown authors· Internet of Things and Artif...· 0 citations
Reliable electrical power availability is essential for various applications, especially in facilities that rely on continuous power supply. To address power interruptions, this study developed an Internet of Things (IoT)-enabled Automatic Transfer Switch (ATS) monitoring system based on an expert system approach for electrical energy backup. The proposed system integrates an ESP32 microcontroller with a ZMPT101B voltage sensor, PZEM-004T power meter, DC voltage sensor, relay module, SIM900A GSM module, inverter, LCD, and a 12 V 35 Ah battery. The system automatically changes the power source from the utility supply (PLN) to the backup battery when a power failure occurs and restores the utility source after normal supply conditions are detected. System conditions and electrical parameters are monitored remotely in real time using the Blynk platform, which also provides system notifications. For decision-making, expert system principles are implemented through a Mamdani Fuzzy Inference System (FIS) developed in MATLAB R2018b, evaluating utility voltage, battery voltage, and load condition to determine the appropriate ATS power-source status. Experimental evaluation at the Instrumentation and Control Laboratory, Universitas Negeri Jakarta, confirmed the system functionality, with average measurement errors of 0.45% for the ZMPT101B sensor and 0.24% for the DC voltage sensor, while the PZEM-004T produced errors of 0.45% for voltage, 3.7% for current, and 0.91% for power measurements. The ATS completed the source transfer within 3 seconds, with the inverter maintaining an output voltage between 217 and 232 VAC. Under a 50 W load, the 12 V 35 Ah battery provided backup power for 3 hours and 30 minutes, and the MATLAB simulation generated a crisp output of 1.86, corresponding to the battery-supplied load condition. Beyond these technical validations, the scientific contribution of this research lies in the successful integration of a Mamdani FIS with IoT-based monitoring to enable adaptive, rule-based decision-making that overcomes the rigidity of conventional fixed-threshold ATS systems. Practically, this intelligent backup solution offers an affordable and reliable alternative for critical infrastructures, such as small-scale healthcare facilities and data centers, particularly in regions with unstable grid conditions. The modular system architecture also provides a scalable foundation for future integration with renewable energy sources and expansion to higher-capacity industrial applications.
Rafiuddin Syam, Ara Akdzal Al Tariq, Efri Sandi et al.· SPEKTRA Jurnal Fisika dan Ap...· 0 citations
