Abstract: Abstract: Scraper conveyor is one of main electrical and mechanical equipment in the mining face, and its reliability has an important significance to production safety. In scraper conveyor reliability life analysis, the linear parameter method is often used to estimate life in traditional Weibull distribution model. But the error of prediction results is larger due to the nonlinear characteristics of fault data. In this paper, a nonlinear BP parameter algorithm is proposed to optimize the model parameters for the scraper conveyor reliability life prediction. Research results show that the BP parameter optimization algorithm has small life prediction error, and raises the accuracy of the scraper conveyor reliability life prediction.