Reconstruction-based fault identification using a combined index

Process monitoring and fault diagnosis are crucial for efficient and optima l operation of a chemical plant. This paper proposes a reconstruction-based fault identification approach using a combined index for multidimensional fault reconstruction and identification. Fault detection is conducted using a new index that combines the squared prediction error (SPE) and T-2. Nece ssary and sufficient conditions for fault detectability are derived. The co mbined index is used to reconstruct the fault along a given fault direction . Faults are identified by assuming that each fault in a candidate fault se t is the true fault and comparing the reconstructed indices with the contro l limits. Fault reconstructability and identifiability on the basis of the combined index are discussed. A new method to extract fault directions from historical fault data is proposed. The dimension of the fault is determine d on the basis of the fault detection indices after fault reconstruction. S everal simulation examples and one practical case are presented. The method proposed here is compared with two existing methods in the literature for the identification single-sensor and multiple-sensor faults. We analyze the reasons that the other two methods lead to erroneous identification result s. Finally, the proposed approach is applied to a rapid thermal annealing p rocess for fault diagnosis. Fault subspaces of several typical process faul ts are extracted from the data and then used to identify new faults.