The online quality control methods for the assembling of remanufactured engines' cylinder block and cover under uncertainty

摘要

The assembling of cylinder block and cover is one of the keys for the quality controlling of remanufactured engines. First, we analyze the critical factors which influence the assembly quality and study the uncertainty connotation of the flatness and roughness of cylinder block and cover, as well as bolts. Then, an uncertainty quantitative measure model for each factor has been structured, and according to that, we proposed a back propagation (BP) neural network-based quality control method which can achieve self-learning, updating, and online dynamic quality controlling. It can reduce the negative effects caused by the uncertainty and improve the assembly accuracy. Finally, the quality data of remanufactured engine in 2012 proves that the method can improve the qualification rate of 0.63% and reduce the cost of after-sales claims by 35.2%; the living examples verify its feasibility and validity.