Dynamic fault detection and diagnosis using neural networks

A neural network methodology for dynamic fault diagnosis is proposed. Moving windows cut the dynamic data into overlapping pieces. Then the segmented data are presented to the networks for training and generalization purposes. Some unique features associated with this methodology, namely the length of the moving window, the sampling rate, and the construction of the training data set, are studied. The proposed method has been successfully applied to a binary distillation process and shows superiority over the networks trained by steady-state data.<>