Research on Rough Set-Neural Network Fault Diagnosis Method
Hao Li · Journal of Northeastern University · 2003
The rough set theory was used to study training sample quality,define relative concept and establish fault feature extraction algorithm for Artificial Neural Network fault diagnosis model. An intelligent rough set neural network hybrid system model was brought forward. The realization steps of the model were analyzed. The validity of these methods was tested by practical examples. Simulation was done using SAS software. The method can solve ANN architecture, sample size,and sample quality,decrease the computation time,and increase the diagnosis correctness.