Nonlinear dynamic systems identification with dynamic neural networks for fault diagnosis in technical processes

Based on the dynamic neuron model-the so called dynamic elementary processor-a dynamic multilayer perceptron neural net (DMLP) is applied to identify black box models of the process. The dynamic adaption algorithm is briefly introduced and compared to other adaption procedures. However, the identified models are used to build the first step of a fault diagnosis scheme (FDS) similar to observer based schemes. The residuals between the measured process output and the outputs estimated by the bank models are used as numerical symptoms for the fault detection and diagnosis. The FDS was successfully applied to monitor the turbine state of a turbosupercharger.<
>