At present, the rapid development of artificial intelligence has provided technical support for many applications, including wireless communication, image recognition, text analysis and other scenarios. Simultaneously, the evaluation of the transmission performance for wireless communication networks is also indispensable. In this paper, based on the proposed wireless relay system experiencing Beaulieu-Xie (BX) fading, we investigate the transmission performance on considering model with derived outrage probability (OP). In order to realize real-time transmission evaluation, an improved sparrow search algorithm (ISSA) intelligent OP prediction method based on back-propagation (BP) neural network is proposed. The results of simulation show that compared with BP and improved cuckoo search algorithm based on BP (ICS-BP) prediction methods, the prediction accuracy of improved sparrow search algorithm based on BP (ISSA-BP) is increased by 50.7%. INDEX TERMS relay networks; OP; BP neural network; Beaulieu-Xie fading channels; ISSA;