Aiming at the PVC production process is complex, the large critical devices polymerizer running need to constantly monitor the characteristics, performance monitoring and fault diagnosis polymerizer for the large PVC batch production process. First of all, for the lack of standard LMBP algorithm, the LMBP neural network algorithm is improved; Secondly, based on the genetic algorithm (GA) and improved LMBP algorithm that based on the GA-improved a LMBP Polymerizer device fault diagnosis algorithm is proposed; improved LMBP algorithm and genetic algorithm (GA) combined algorithm is applied to the study of fault diagnosis polymerizer. Finally, Combined with polymerizer industrial field history data set to carry out fault diagnosis simulation, results show the mentioned GA-improved LMBP fault diagnosis method. is effectiveness