This paper presents the design of a Spiking Neural Network (SNN) structure for control applications and evaluates its performance on a servo system. The design of SNN is performed using Spike Response Model (SRM). A gradient algorithm is applied for learning of SNN. The coding and decoding is applied for converting real numbers into spikes. A number of different load conditions including nonlinear and time-varying ones are used to investigate the performance of the proposed control algorithm on a laboratory setup that regulates the speed of a DC motor. It is seen that the control structure proposed has the ability to regulate the servo system around the set point signal in the presence of load disturbances.