Data-Driven Design of Fault Diagnosis Systems

In many industrial applications early detection and diagnosis of abnormal behavior of the plant is of great importance. During the last decades, the complexity of process plants has been drastically increased, which imposes great challenges in development of model-based monitoring approaches and it sometimes becomes unrealistic for modern large-scale processes. The main objective of Adel Haghani Abandan Sari is to study e cient fault diagnosis techniques for complex industrial systems using process historical data and considering the nonlinear behavior of the process. To this end, di erent methods are presented to solve the fault diagnosis problem based on the overall behavior of the process and its dynamics. Moreover, a novel technique is proposed for fault isolation and determination of the root-cause of the faults in the system, based on the fault impacts on the process measurements.

In many industrial applications early detection and diagnosis of abnormal behavior of the plant is of great importance. During the last decades, the complexity of process plants has been drastically increased, which imposes great challenges in development of model-based monitoring approaches and it sometimes becomes unrealistic for modern large-scale processes.

Introduction.- An overview of fault diagnosis techniques.- Fault detection in multimode nonlinear systems.- Fault detection in multimode nonlinear dynamic systems.- Fault diagnosis in multimode nonlinear processes.- Bayesian approach for fault treatment.- Application and benchmark study.- Summary.