Study of the Auxiliary Robot Used to Disassemb and Assemb Mid-Set Switch Cubicle Based on BCI

摘要

In order to solve the problem that the working space of the central switchgear is limited or the current transformer is limited, and the single person cannot complete the operation, the brain-computer interface (BCI) technology is applied to the actual operation. In this paper, the 5 (0-4 Hz) and 9(4-8 Hz) sub-bands of EEG signals are obtained by wavelet decomposition (WD). The relationship between the 14 pairs of EEG channels was determined using the Pearson correlation coefficient. The motion characteristics are then analyzed using the validity of brain network parameters. At the same time, eye movement features are extracted from the F3 and F4 channels. Finally, the movement characteristics identified by the brain network and eye movement features can aid in the disassembly and assembly of the transformer. The experimental results show that the accuracy of left and right motion recognition is over 97%. Compared with the traditional disassembly method, the efficiency has increased by nearly 60%.