The Psychological State Evaluation Method of a Main Control Room Operator Based on Physiological Signals

In this study, workload and mental fatigue were taken as research objects to evaluate the psychological state of nuclear power plant operators based on EEG and ECG physiological signals. Fatigue induced experiment and workload evaluation experiment were designed respectively. In the fatigue induced experiment, the operator had to deal with the Steam Generator Tube Ruptures (SGTR) accident task and SGTR tasks with additional minor accidents. In the workload evaluation experiment, the operator had to deal with a small breach Loss of Coolant Accident (LOCA) task and a large breach LOCA task. EEg and ECG signals of the operator were collected before and after the experimental task. The results of fatigue induced experiment showed that there were significant differences between 5 indexes of heart rate variability and 15 indexes of EEG before and after the experimental task. Mental fatigue was divided into two levels: awake and fatigue. Based on the above physiological indexes, a mental fatigue classification model was established by Gauss naive Bayes algorithm, and its accuracy was verified to be 80.0%. The results of workload evaluation experiment showed that there were significant differences in 31 indexes of EEG. The workload was classified into two levels, low workload and high workload, and based on the above 31 EEG indexes, a workload assessment model was established using the fine-tree algorithm, and its accuracy was verified to be 89.3%.