The application relates to the technical field of brain-computer interfaces, and discloses an intelligent
rehabilitation wheelchair based on a brain-computer interface and a control method thereof, wherein the method comprises the following steps: S1: collecting a first electroencephalogram
signal of a user's motor cortex, pre-
processing the first electroencephalogram
signal, and obtaining a second electroencephalogram
signal; S2: classifying the second electroencephalogram signal, decoding a
wheelchair motion instruction, and calculating a
cognitive load level according to the second electroencephalogram signal; and S3: generating a
wheelchair speed parameter and a wheelchair
turning radius according to the
cognitive load level, and driving a wheelchair motor to perform a corresponding motion action based on the wheelchair motion instruction, the wheelchair speed parameter and the wheelchair
turning radius. The method improves the motion intention decoding accuracy and reduces the decoding
delay, and solves the problem of insufficient decoding performance caused by signal redundancy of a traditional model.