This paper presents a study of detection performance of Bayesian linear model (BLM) detector for amplify and forward (AF) cooperative communication systems in Rayleigh fading channels. We consider that signals propagation between the source and destination suffer from destructive effects such as noise, multi-path fading, shadowing and other channel impairments. Therefore, BLM detection in relay networks is a proposed method to improve the signal detection performance and to reduce the implementation complexity of the system. The system performance is analyzed in terms of probability of detection against the probability of false alarm and probability of missed detection against the probability of false alarm knows as receiver operating characteristics (ROC) and complementary ROC respectively. Matlab simulations and results analysis are presented. The results showed that the proposed method can be effective in improving the detection performance in AF relay networks.