A Wearable Device-Based Proactive Warning System for Smart Grid Substations Using Fuzzy Neural Networks

Multidimensional monitoring and proactive warning of operational states in smart grid substations are essential for ensuring the safety and stability of grid operations. Here, we present a proactive warning model with a multidimensional perspective, tailored to address differentiated business requirements. The model combines flexible wearable devices with fuzzy neural networks to enable intelligent monitoring and early warning by collecting, fusing, dynamically mapping, and analyzing real-time data from substations. Experimental evaluations on a public substation dataset, supplemented by validation using a prototype system deployed in a real substation environment, demonstrate that the proposed model surpasses existing platforms in warning accuracy, response time, and resource efficiency. The model achieves a warning accuracy of 96.7% and a response time of 1.5 seconds, while maintaining strong adaptability and robustness under diverse and complex conditions. Despite its demonstrated effectiveness, challenges remain, including limited data coverage and the need for optimization in real-time computational capabilities. Future research will focus on diversifying data sources, developing more efficient computing frameworks, and broadening the system's applicability. This study provides an innovative solution for multidimensional operational state monitoring and proactive warning in smart grid substations, offering a valuable reference for advancing research in this domain.