Control Machine Arm Movement The Surface Emg Transform Regular Studies

Surface electromyographic (sEMG) signals can be monitored noninvasively by using electrodes on the skin surface. They are the summation of all motor unit action potentials(MUAP)within the pick—up area of the electrodes, so they provide information of the neuromuscular activities of the examined muscle. In addition, these signals have been not only widely applied to clinical diagnosis, sports medicine, ergonomics, rehabilitation medicine, neurophysiology and electrophysiology, but also suggested and utilized as an effective method to provide control commands for artificial limbs and functional neuromuscular stimulations.With the development of signal method and computer technology, effective signal feature extraction and accurate function identification are the crucial problem involved in practical prosthesis control. These problems were discussed theoretically and practically in this paper. The major contents of this thesis are as follows:1. When upper limbs do flexion movement, we collect sEMG of biceps, then by wavelet transform and Matlab to do de-noising of sEMG.2. In order to identifying different patterns, the first thing we should do is to extract the characteristic of the EMG signal. This thesis uses a multi-scale wavelet transform to analyze the signals and creatively proposes a new method to create characteristic vector that is specific and simple.3. This paper tries to improve the BP neural network by means of various improved algorithms, such as Levenberg-Marquardt. Experimental result shows that this improved neural network not only is able to identify the movement of upper limbs, but also improves the neural network on speed and accuracy, and overcomes the immanent drawbacks of the BP neural network, which has a great potential in practical application of prothesis control.4. The relationship between the sEMG signal on biceps and the power level was studied. Then, we analyzed the relationship between the characteristics of sEMG and power level. The test result indicates that there exists positive correlation between the characteristics of biceps'sEMG and the power level.