Abstract: In order to realize the real-time prediction of motor torque, an output torque prediction model is proposed based on Least Square Support Vector Machine (LS-SVM).Based on the analysis of the composition of an electrical system, the load spectra obtained from underground power test and underground mine roadway are taken as training and test samples, the authors make the use of the hybrid scraper motor actual speed, the DC terminal current of motor, the DC terminal voltage of motor, the motor controller temperature and the motor winding temperature as the input, the output torque of the motor is used as the output, thus, the model based on least square support vector machines (LS-SVM) can reflect the influence factors of motor output torque more comprehensively.Experiment results show that the proposed model has a good prediction accuracy and suitable ability.