Incipient fault detection and diagnosis using statistical signal processing

The requirements for a fault detection and diagnosis method are the following:

• The simplicity that is defined as the amount of information for processing;

• The sensitivity that is defined as the capability of the method to detect a fault at its earliest stage;

• The robustness that measures the capability of the method to perform despite the perturbations.

The fault detection and diagnosis methods can be broadly classified into three families; physics-based, qualitative-based and data-driven. The objective of this presentation is to examine the case of incipient fault and show the benefits of data-driven approach with the use of global indicator based on the statistical properties of the information.

讲座人简介:

Prof. Demba DIALLO (IEEE SM’05) received the M.Sc. and Ph.D. degrees both in Electrical and Computer Engineering, from the National Polytechnic Institute of Grenoble, France, in 1990 and 1993 respectively. After graduation, he worked from 1994 to 1999 as a Research Engineer at the Electrotechnic Laboratory of Grenoble, France, on electrical drives and active filters. In 1999, he joined the University of Picardie as Associate Professor of Electrical Engineering. Since September 2004, he has been joining the Technological Institute of Cachan, University of Paris Sud and the Electrical Engineering Laboratory of Paris as an Associate Professor. Since 2009, he is a Full Professor. His area of academic and industrial research includes advanced control techniques and diagnosis of AC drives, renewable energies, design of electric powertrains and automous systems. He is Editor of the IEEE Transactions on Vehicular Technology and the International Journal on Energy Conversion (IRECON). He is the director-elect (2018-2021) of the French National Research Group on Electrical Engineering.

欢迎感兴趣的师生参加!

回顶部