Multiple-fault diagnosis in induction motors through support vector machine classification at variable operating conditions

摘要: This work presents a fault diagnosis strategy for induction motors based on multi-class classification through support vector machines (SVM), and the so-called one-against-one method. The proposed approach classifies four different motor conditions (healthy, misalignment, unbalanced rotor bearing damage) at variable operating (supply frequency load torque). SVMs use signatures from domain characteristics related to each studied fault. These combine information just stator condition: radial vibration currents. To acquire training validation data in steady state, experiments were performed using three-phase motor. Thirty-five sets obtained regimes of specific (140 including no-fault scenario) validate our study. with Gaussian basis function (RBF) as kernel nonlinear process. select parameter value RBF, bootstrap technique was used. resulting accuracy process range 84.8–100%.