Fan Improved Algorithm of BP Neural Network Fault Diagnosis Research

According to the structure of the BP neural network and the algorithm, choose three methods of BP neural network algorithm was improved, through analysis and comparison, computing speed is faster, more accurate judgment Levenberg Marquardt algorithm as the improved algorithm of optimal; Using the algorithm to the established BP neural network for training analysis; Then use the Matlab software, the fan fault feature data for training; Complete the neural network with the training of a group with different fault types of test data, judge the fault types, validation Levenberg Marquardt authenticity and validity of the algorithm.