Fault detection in non-linear systems based on type-2 fuzzy logic

Abstract

This paper presents a new method for fault detection (FD) based on interval type-2 fuzzy sets. The main idea is based on a confident span using interval type-2 fuzzy systems. An estimate for upper and lower bounds of output has been taken using the designing of an optimal fuzzy system through clustering. Finally the method has been tested in two non-linear systems, a two-tank with a fluid flow and pH neutralisation process, and it is compared with a well-known method named ANFIS. Furthermore, the mathematical model and the results of simulations prove the effectiveness, usefulness and applications of our new method.

Keywords:

• fault detection
• fuzzy model
• interval model
• clustering
• type-2 fuzzy logic systems

Additional information

Notes on contributors

Behrooz Safarinejadian

Behrooz Safarinejadian received his BS and MS degrees from the Electrical Engineering Department, Shiraz University, Shiraz, Iran, in 2002 and 2005, respectively. He received his Ph.D. degree from the Electrical Engineering Department, Amirkabir University of Technology, Tehran, Iran, in 2009. Since 2009, he has been with the Faculty of Electrical and Electronic Engineering, Shiraz University of Technology, Shiraz, Iran. His research interests include computational intelligence, control systems theory, estimation theory, statistical signal processing and fault detection.

Parisa Ghane

Parisa Ghane received her BS degree in electrical engineering in 2012 from Shiraz University of Technology, Shiraz, Iran. Since then she has been a member of research groups. Her main research interest areas are computational intelligence and its applications in control, resilient systems and time-delay systems.

Hossein Monirvaghefi

Hossein Monirvaghefi received his BS degree in electrical engineering–control systems in 2010 from Shiraz University of Technology, Shiraz, Iran. He is a Master's student of control engineering at Khaje Nasir Toosi University of Technology and currently studies control performance monitoring (CPM) methods as a member of advanced process and automation control (APAC) group at Khajeh Nasir Toosi University of Technology, Tehran, Iran.