Abstract: A novel neural network quantum genetic algorithm is proposed to solve the problem of the lower accuracy in the scraper conveyor fault diagnosis process. Based on quantum genetic theory, the neural network weights and threshold are optimized, and accelerate solve. Theory analysis and preliminary results show that the proposed quantum genetic algorithm combined with BP neural network can effectively overcome the disadvantage of the slower convergence and falling easily into local minimum in neural network, and raise the identification precision in scraper conveyor fault diagnosis.