Robust fault diagnosis in catalytic cracking converter using artificial neural networks
Abstract
The paper presents designing of a robust fault diagnosis system for a catalytic cracking processusing artificial neural networks. Identification of the considered process is carried out by usingrecurrent neural networks. To achieve a robust fault diagnosis system, an uncertainty associatedwith the model is also taken into account. Neural version of the Model Error Modelling is used todeal with two main uncertainty sources: unmodelled dynamics and noise corrupting the data. Theproposed approach is tested on the example of catalytic cracking converter at the nominaloperations condition as well as in the case of faults.
