Motor current signature analysis is cited in many articles to detect the rotor bar fracture. Because of the small amplitude at the fault frequency relative to the main frequency amplitude, the former cannot be easily distinguished from the latter. As a solution, a method based on the algebraic identity of trinomial expansion of the stator current is proposed which enables us to display the difference between the frequency of the fault signature and the base frequency. In addition, the components at unwanted frequencies are attenuated using low-pass-filter. After that, the frequency weighting techniques are used to magnify the component at the target frequency compared to the lower frequencies than it. Indeed, a weighting method based on differentiation is used and another method based on convolution is proposed as tools to enhance the clarity of the frequency spectrum display for a broken rotor bar. To validate the proposed methods, they are examined on the laboratory data obtained from three different operating conditions including the direct online start, the direct torque control, and the scalar control and the results show the ability of the proposed methods in fault detection of an induction motor.