In an article published in the journal Plos One, researchers investigated fire hazards caused by power equipment overheating with the help of artificial intelligence (AI), blockchain, and Internet of Things (IoT). Focused on IoT equipment monitoring in smart grids, they established a tailored temperature monitoring network for wireless power equipment.
Study: AI, Blockchain, and IoT: Revolutionizing Power Equipment Safety. Image credit: Eakrin Rasadonyindee/Shutterstock
Background
The escalating failure rate of power equipment in modern electric power engineering has heightened the risk of accidents, including fires caused by delayed fault removal. Timely detection of abnormal heating is crucial, necessitating robust temperature monitoring systems. Existing literature highlights the increasing global interest in electric power engineering safety, particularly in power temperature testing and monitoring technology.
Noteworthy advancements include the application of IoT, blockchain, and AI in various domains, such as beamforming strategies, infrared temperature monitoring, and fault prediction using temperature data. Despite these strides, there are gaps in current research, such as limited exploration of blockchain potential in IoT connectivity, insufficient data privacy protection, and the need for more robust intelligent data analysis models.
This study aimed to bridge these gaps by designing a comprehensive temperature monitoring network for IoT wireless power equipment. It incorporated AI and blockchain technologies to enhance data privacy, security, and intelligent analysis, addressing the limitations of existing research. The proposed system not only facilitated real-time monitoring and remote temperature measurement but also introduced a proactive protective mechanism for issuing timely warnings, preventing high-temperature fires.
Leveraging IoT technology, the research introduced wireless sensor temperature measurement capable of real-time monitoring and early warnings. The integration of AI-enhanced temperature data analysis for intelligent anomaly detection while blockchain ensured data security and traceability.
Methods and materials
The research employed a multi-faceted approach, incorporating IoT, AI, blockchain, and wireless sensor networks (WSN) to design an intelligent and secure wireless temperature measurement system for power engineering. The IoT technology, evolving since its proposal in 1999, served as the foundation for connecting various objects to the internet through information-sensing equipment. Integrating AI and blockchain technology formed a robust solution for temperature data analysis and security within the power system.
AI was applied for intelligent analysis of temperature data from power equipment, providing real-time fault warnings and anomaly detection. This enhanced the safety of power equipment operations and elevated the system's intelligence. The combination of AI and blockchain ensured data integrity, transparency, and privacy protection. Blockchain, acting as a decentralized network, enhanced the security and trustworthiness of power-related data, preventing tampering and ensuring traceability.
The wireless sensor temperature measurement system utilized WSN to integrate the physical and information world. The system's design considerations included minimizing spatial occupancy, ensuring reliable wireless communication, anti-interference performance, and cost-effectiveness. The Finite Element Method (FEM) was employed to establish a temperature field distribution model for power systems, providing accurate and reliable temperature data.
The overall scheme of the proposed IoT-based wireless temperature monitoring system for power engineering involved decentralized wireless sensors interconnected through IoT technology. The wireless temperature monitoring system facilitated real-time data collection, early fault warnings, and anomaly detection, contributing to efficient power equipment maintenance and preventing accidents. The experimental phase involved the installation of 30 temperature sensors, 15 temperature measuring devices, and 2 monitoring hosts, emphasizing the practical implementation and validation of the proposed system.
Results
The experiment conducted in the power laboratory aimed to evaluate the performance of a wireless temperature measurement system supported by IoT in electric power engineering. The results demonstrated high accuracy in temperature measurement, with an error range within 0.1°C. The system's capability for real-time monitoring of remote power equipment temperature was highlighted, enabling the identification of potential high-temperature risks and timely dispatch of maintenance personnel.
The wireless temperature nodes, designed with low power consumption emphasis, underwent battery life tests, confirming minimal voltage increase and extended battery life. Temperature out-of-limit alarm tests, including temperature overrun alarms, device power loss alarms, and device communication fault alarms, showed successful alarm signal transmission and reception. This ensured that the system effectively alerted power workstation staff and allowed timely preventive measures to be taken, minimizing the risk of fire and associated losses.
Long-term stability, load variation impact, security, and scalability of the IoT wireless temperature monitoring network were assessed. The system exhibited high stability, with temperature monitoring errors fluctuating within a small range, data stability maintained, and temperature detection accuracy consistently above 95%.
Under various load conditions, the system demonstrated rapid response times and accuracy in monitoring temperature changes and adapting to fluctuations in power equipment loads. Security tests indicated a high recognition rate for network attacks and data integrity maintenance against tampering. Network scalability tests confirmed the system's robust performance under varying network loads, expanding data processing capacity while maintaining stable operations.
Conclusion
In conclusion, integrating AI and blockchain technologies enhanced the intelligence of wireless temperature monitoring systems in power engineering, enabling accurate fault prediction and proactive measures. The proposed IoT-based wireless temperature measurement system demonstrated high accuracy, aligning closely with actual values. For further improvement, future research should focus on optimizing transmission power and power consumption.
IoT and Machine Learning for Pure Gas Detection