Fault diagnosis using partial syndromes: a modified Hopfield neural network approach

Abstract

This paper presents a modified Hopfield neural network (HNN) for solving the system-level fault diagnosis problem which aims at identifying the set of faulty nodes. This problem has been extensively studied in the last three decades. Nevertheless, identifying the set of all faulty nodes using only partial syndromes, i.e. when some of the testing or comparison outcomes are missing prior to initiating the diagnosis phase, remains an outstanding research issue. The new HNN-based diagnosis algorithm does not require any prior learning or knowledge about the system, nor about any faulty situation, hence providing a better generalisation performance. Results from a thorough simulation study demonstrate the effectiveness of the HNN-based fault diagnosis algorithm in terms of diagnosis correctness, diagnosis latency and diagnosis scalability, for randomly generated diagnosable systems of different sizes and under various fault scenarios. We have also conducted extensive simulations using partial syndromes. Simulations showed that the HNN-based diagnosis performed efficiently, i.e. diagnosis correctness was around 99% when at most half of the test or comparison outcomes are missing, making it a viable alternative to existing diagnosis algorithms.