Induction motors are widely used in industry due to their simple and powerful design as well as for their proven reliability. Despite these advantages, the environment within which they operate, may create unfavorable conditions leading to operational faults and reduction in the performance of the motor (e.g., increased power consumption, increased maintenance cost, halt of operation).To avoid lengthy disruptions and provide high reliability in motor operation, there are numerous fault prediction algorithms, proposed in the bibliography, to reduce implications in motor operation by evaluating the state of the motor at any given time and alarming maintenance staff of an upcoming fault. However, despite the wide variety of prediction techniques, the majority of these prediction algorithms are hard to implement (i.e., complicated algorithms, high deployment cost, vaguedescriptions) restricting the applicability and usefulness of the techniques.In this study, we present a systematic methodology for fault diagnosis in induction motors using the Takagi – Sugeno framework. Our technique, simplifies the implementation of prediction algorithms, reduces the installation and maintenance costs of an induction motor, and enables the application of similar prediction techniques to a wider set of applications.