EDST

Industrial Fault Detection and Isolation (FDI) become more essential in light of increased automation in industry. The significant increase of systems and plants complexity during last decades made the FDI tasks appear as major steps in all industrial processes.

In this thesis, adaptive intelligent techniques based on artificial neural networks combined with advanced signal processing methods for systematic detection and diagnosis of faults in industrial systems are developed and put forward. The proposed on-line classification techniques consist of three main stages: (1) signal modeling and feature extraction, (2) feature classification and (3) output decision. In first stage, our approach is relied on the assumption that faults are reflected in the extracted features. For feature classification algorithm, several techniques based on neural networks are proposed. A binary decision tree relied on multiclass Support Vector Machine (SVM) algorithm is put forward. The technique selects dynamic appropriate feature at each level (branch), and classify it in a binary classifier. Another advanced classification technique is anticipated based on mapping algorithm network that can extract features from historical data and require prior knowledge about the process. The significance of this network focuses on its ability to reserve old data in equitable probabilities during the mapping process. Each class of faults or disturbances will be represented by a particular surface at the end of the mapping process. Third contribution focuses on building network with nodes that can activate in specific subspaces of different classes. The concept behind this method is to divide the pattern space of faults in a hierarchical way into a number of smaller sub-spaces depending on the activation zones of clustered parameters. For each type of faults, in a particular sub-space, a special diagnosis agent is trained. An advanced parameter selection is embedded in this algorithm for improving the confidence of classification diagnosis. All contributions are applied to the fault detection and diagnosis of various industrial systems in the domains of mechanical or chemical engineering. The performances of our approaches are studied and compared with several existing neural network methods and the accuracy of all methodologies is considered carefully and evaluated.