Абстрактный

EFFICIENT COMPARISON BASED SELF DIAGNOSIS USING BACKPROPAGATION ARTIFICIAL NEURAL NETWORKS

Radha J, Mrs Manjula Devi T H

In this paper, a comparison based diagnosis model is used for system-level fault diagnosis in a network. In comparison based diagnosis model, tasks are made to pair of nodes and their outcomes are compared by neighbouring nodes. In this comparison it is possible for the situation like faulty nodes can incorrectly claim that fault-free nodes are faulty or that faulty ones are fault-free. So to overcome this, a new diagnosis approach is proposed which uses neural networks to solve the fault identification problem using partial syndromes. Results obtained using partial syndrome method will show that neural-network-based diagnosis approach provide good results making it an alternative to existing diagnosis algorithms