Abstract: Now a days air conditioning system is the necessity part of human life. The different controllers used for controlling air conditioning system like on-off controllers or PID controllers. But these controllers cannot give the sufficient response and consume high power. This paper aims to control the air conditioning system such that the output temperature of air conditioning systems are getting as required by the operator with fast response and low consuming power. For this purpose neural network controllers are designed which is feedback to the air conditioning system. We designed such neural network control system that speculates its own control law. The advantage of using neural networks are this controller is self-learning system and give the faster and better response with comparison to another controllers and give the zero overshoot output.