Research on Muscle Fatigue Grade and Surface EMG signal Based on DP_PSO_SVR Model

Aiming at the problem of unclear classification of traditional muscle fatigue levels, a joint analysis method of surface electromyography (sEMG) and muscle physiological pH is proposed. This method uses AnyBody muscle strength analysis software to analyze the muscle force, combined with the time domain and frequency domain characteristic parameters of the surface EMG signal. In order to compensate for the non-linear and non-stationary characteristics of the EMG signal, the time-frequency domain characteristic value of the EMG signal-wavelet is introduced Pack coefficient variance. In order to improve the accuracy of muscle fatigue grade classification, the dual-group particle swarm optimization algorithm was used to optimize the support vector machine regression (DP_PSO_SVR). By analyzing the change law of sEMG and muscle pH value during upper limb fatigue, a fatigue grade analysis model based on DP_PSO_SVR was established. Realize the judgment of the degree of upper limb muscle fatigue.