Fault detection of systems with redundant sensors using constrained Kohonen networks

The Kohonen self-organizing map (KN) was developed for pattern recognition, and has been extended to fault classification. However, the KN cannot be a pplied to classify faults from the system output if it contains other facto rs, such as system state and sensor mounting errors. To overcome this probl em, a constrained KN (CKN) is proposed. To eliminate the effect of the syst em state and the mounting errors, it is proposed that the weight vectors of the CKN are constrained in the parity space. The training algorithm of the CKN is derived, and its convergence discussed. Application of the CKN to f ault classification is presented, and its performance is illustrated by an example involving a redundant sensor system with six sensors. (C) 2001 Else vier Science Ltd. All rights reserved.