智能轮椅作为性能优越的代步工具，在康复和助残领域应用广泛。人机交互方式作为智能轮椅系统的关键技术之一，越来越受到人们的重视。脑-机接口技术（Brain Computer Interface，BCI）作为一种涉及神经科学、信号检测、信号处理、模式识别等多学科的人机交互方式，在大脑和外界设备之间建立起直接的通信和控制通道，使严重神经或肌肉伤残患者使用智能轮椅成为可能。 自步调脑-机接口（Self brain computer interface，SBCI）允许用户在任何时候按照自己的意愿控制外接设备，运动想象脑-机接口作为一种典型的自步调脑-机接口，得到了广泛的研究。脑电中存在与运动相关的特异性成分，当人们在运动准备或想象单侧肢体运动（左右手）时，大脑对侧的运动感觉区的μ（8-12Hz）节律和β节律（13-30Hz）能量减小，这就是事件相关去同步（Event-Related Desynchronization, ERD）和事件相关同步（Event-Related Synchronization, ERS）现象。脑电信号的ERD 和ERS 现象成为运动想象脑-机接口的生理基础。 本文基于运动想象脑-机接口技术，设计并实现了结合脑-机接口技术的智能轮椅系统，其中主要工作有以下几个方面： 首先，设计并实现了便携式脑电采集设备，增强了EEG数据采集的方便性，实现了随时随地的EEG数据采集，扩展了BCI系统的应用范围。在大脑皮层的特定区域放置脑电极获取被试者的脑电,经过信号调理电路放大和滤波以后，由微控制器对脑电信号采样并数字化，通过无线传输技术上传给电脑。 其次，设计并实现了轮椅控制电路。通过对电动轮椅控制原理的研究，对轮椅控制器进行了改造，设计并实现了接口电路，从而实现了脑电分类结果对电动轮椅方向的直接控制。 最后，对便携式脑电采集设备和轮椅控制电路进行了测试。通过测量被试不同注意力情况下的脑电信号，有效检测到了不同任务下alpha波的变化，验证了采集设备的有效性。通过串口发送命令，实现了对轮椅方向的有效控制，验证了轮椅控制电路的有效性。

As a transport, intelligent wheelchair has superior performance which makes it widely applied in the field of rehabilitation and assistive. Human-computer interaction, as one of the key technologies of intelligent wheelchair system, draws more and more attention. Brain - Computer Interface (BCI) technology as a human-computer interaction technologies covering neuroscience, signal detection, signal processing, pattern recognition, etc, establish a direct communication and control channel between the brain and the outside world, enabling patients with severe neurological or muscular disabilities to use intelligent wheelchair. Self-paced brain computer interface (SBCI) systems allow individuals to control outside device using EEG signals at their own pace, motor imagery BCI as a typical SBCI system, has been extensively researched. There are motor-related specific components in EEG. When people prepare or imagine unilateral limb movements (left or right hand), the power of μ (8-12 Hz) rhythm and β rhythm (13-30 Hz) in contralateral motor sensory areas decreases, and the power of ipsilateral increases, all these is consequence of a large brain neurons postsynaptic potential mutual weaken and enhance. This is so-called event related desynchronization (ERD) and event-related synchronization (ERS). ERD/ERS phenomena are the physiological basis of motor imagery BCI. Based on motor imagery BCI technology, this thesis design and implement a intelligent wheelchair system combined with BCI technology. The main work of this thesis includes: Firstly, the design and implementation of a portable EEG acquisition equipment. It enhances the convenience of EEG data acquisition, collecting EEG data at anytime and anywhere and thus extends the scope of application of BCI system. EEG signal is recorded through electrodes placed in specific area of the cerebral cortex, and then amplified and filtered EEG by the signal processing circuit and sampled and digitalized by microcontroller. The last step of portable EEG acquisition equipment is to upload data to the computer through wireless transmission technology. Secondly, the design and implementation of a wheelchair control circuit. Based on the study of control principle of the electric wheelchair, the wheelchair controller is transformed and interface circuit is designed and implemented. Thus the EEG classification results control the direction of electric wheelchairs directly.Finally, the portable EEG acquisition equipment and the wheelchair control circuit are tested online. By measuring brain signals under different attention cases, alpha waves’ changes are effectively detected, verifying the validity of acquisition equipment. Sending commands through the serial port to wheelchair, the direction is effectively controlled, proved the effectiveness of the control circuit.