a b s t r a c tThree-phase induction motors (TIMs) are the key elements of electromechanical energy conversion in avariety of productive sectors. Identifying a defect in a running motor, before a failure occurs, can providegreater security in the decision-making processes for machine maintenance, reduced costs and increasedmachine operation availability. This paper proposes a new approach for identifying faults and improvingperformance in three-phase induction motors by means of a multi-agent system (MAS) with distinctbehavior classifiers. The faults observed are related to faulty bearings, breakages in squirrel-cage rotorbars, and short-circuits between the coils of the stator winding. By analyzing the amplitudes of the currentsignals in the time domain, experimental results are obtained through the different methods of patternclassification under various sinusoidal power and mechanical load conditions for TIMs. The use of an MASto classify induction motor faults allows the agents to work in conjunction in order to perform a specificset of tasks and achieve the goals. This technique proved its effectiveness in the evaluated situations with1 and 2 hp motors, providing an alternative tool to traditional methods to identify bearing faults, brokenrotor bars and stator short-circuit faults in TIMs.