Step motors are well established, and easily found in FA,OA applications. The conventional step motor controllers cause the step motor to move through a full step or a half step per input pulse depending upon the excitation sequence used. The main drawbacks are limited resolution and vibration. Microstep control of stepmotor is usually thought of as an extension of conventional step motor control technology. The essence of micro stepping is that we divide the full step of a stepmotor into a number of substep called microstep and cause the stepmotor to move through a substep per input pulse. In ideal case, by controlling the individual phase currents of a two-phase step motor sinusoidally we can get uniform torque and step angles. But due to the nonlinear characteristics of the step motor, we need to compensate current waveform to improve the overall smoothness of the conventional micro stepping system. Torque is consist of many harmonics. Fourier transform techniques can be applied to the torque equation to derive the harmonic structure of the torque produced at constant rotor velocity by both sinusoidal and compensated phase current waveforms. Detent torque was one of the most dominant factors of vibration for two phase Hybrid step motor we used. We implement digital Pulse Width Modulation(PWM) driver to drive step motor and microphone was used for detecting vibration of step motor. Driver enables speed change automatically by increasing or decreasing micro stepping ratio which we call Automatic Switching on the Fly. In this thesis, to compensate the torque harmonics, Neural Networks is applied to the system and we found compensated optimal input current waveform. Finally we can get smooth motion of step motor in a wide range of motor speed.
