The Parity Space-based Fault Detection for Linear Discrete Time Systems with Integral Measurements

Abstract

In this work, we investigate the fault detection (FD) problem based on parity space for linear discrete time systems with integral measurements. The traditional parity space-based FD method is no longer applicable to the systems with integral measurements. The transfer matrices need to be redesigned to make the traditional parity relation still hold. Moreover, an algorithm is also provided to compute the transfer matrices and the singular value decomposition (SVD) is used to design the parity space matrices. Finally, an illustrative example about a three-tank system is demonstrated the availability of our proposed approach.