Design Of EEG-controlled Electric Vehicle System

EEG signal reflects the rhythmic movement of brain neurons and has important research value in clinical medicine and rehabilitation engineering.The brain-machine interface technology provides the possibility of information exchange between the brain and the external computer equipment.The technology does not rely on the participation of the limb nervous system and muscle tissue,making the "idea" become "action" and has important theories.The scientific research value also has broad practical application prospects and has become a research hotspot in biomedical engineering and other fields.The research on brain-electrical signals based on sports imagination is a very important branch of the brain-computer interface.This paper mainly studies the method of EEG control based on the recognition of multi-class consciousness tasks.Starting from the research background and research significance of the subject,the features of EEG signals are described,and the preprocessing methods,feature extraction methods,and pattern recognition methods of EEG signals are analyzed.Using brain gear AM chip developed and produced by Neurosky Corporation in the United States to extract EEG signals,and using the Fast ICA algorithm to preprocess the extracted EEG signals,and then applying the dual-tree complex wavelet-co-space to the preprocessed EEG signals.A pattern method is used to extract features.Then a multi-core learning support vector machine is used to classify and identify the extracted feature vectors.A hardware circuit that meets the requirements is designed,including the main control circuit,system communication circuit,and motor drive circuit.Electrical signals control the electric car's forward,left,right and stop.The performance of the electric vehicle experimental platform was tested and good experimental results were obtained.Compared with the traditional methods for extracting EEG signals,the dualtree complex wavelet-common space mode algorithm used in this paper makes the number of channels of EEG signal less,and the data operation time becomes shorter,which improves the efficiency and anti-jamming performance.This makes the extraction of EEG signals simple and accurate.