Abstract: Abstract: Aimed at the complexity of the fan unit fault, a fault diagnosis method based on the BP neural network optimized by the genetic algorithm (GA-BP) is adopted. According to the normalized failure characteristics samples and desired output, the diagnosis network is trained for the standard goal. By testing the validation data through the trained net, the results show that the method meets the requirements of speed and accuracy in diagnosis and has practical application value. The paper lays the foundation for bettering fan vibration fault diagnosis technology.

Key words: Key words: fan unit, fault diagnosis, genetic algorithm, BPneural network