This paper presents a proposed sensorless algorithm for induction motor(IM)speed control based on artificial neural networks (ANNs).The Indirect rotor field oriented (IRFO) technique is applied to control the motor. It is designed based on the proportional-integral (PI) controller. The particle swarm optimization (PSO) algorithm is used as a good solution for the problems associated with the design of the proportional-integral (PI) controller gains.The PSO is compared with the conventional methods. The proposed controller (PSO-PI) is then integrated with the artificial neural network(ANN) speed estimator. The MATLAB/Simulink is used for the simulation of the system. The obtained simulation results for the proposed technique are very close to the actual ones.