EEG-based emotion recognition for high-voltage safety operating procedures

The safety of high-voltage operating procedures is paramount in the power industry, where emotional stress, fatigue, and cognitive strain can severely impact an operator’s performance, attention, and decision-making. Traditional safety monitoring systems largely overlook these psychological dimensions, focusing instead on physical safety measures. This paper presents an innovative EEG-based emotion recognition framework designed specifically for high-voltage safety operations, addressing this critical gap by providing continuous, real-time assessment of operators' emotional states. The proposed system integrates EEG data with multi-sensor physiological and psychological metrics, enabling real-time monitoring, in-depth analysis, and proactive alerts for pre-, during-, and post-operation phases. Advanced machine learning techniques are employed to extract meaningful patterns from EEG signals, allowing for the early detection of emotional states and cognitive risks. This approach facilitates data-driven decision-making and adaptive interventions to enhance operational safety and reduce error rates in high- stakes environments. The framework’s novelty lies in its continuous, dynamic assessment of cognitive load and emotional state, offering a scientifically grounded, practical tool to improve safety and efficiency in high-voltage operations.