Distributed Reflectometry for Soft Fault Identification in Wired Networks Using Neural Network and Genetic Algorithm

Based on the Multi-Carrier Time Domain Reflectometry (MCTDR) technique, new methods which could detect, locate and characterize multiple soft faults in complex wired networks are proposed in this paper. The first method combines the MCTDR with the Multi-Layer Perceptron Neural Network (MLP-NN), the second one combines the MCTDR with the well-known genetic algorithm (GA). Furthermore, in order to allow effective monitoring without ambiguity, a branched network is diagnosed by several reflectometers (sensors) at the different extremities. The main novelty here lies in the fact that the NN and GA methods are used for data fusion from several distributed reflectometers. The needed datasets for training and testing the NN are generated by simulation using MCTDR responses. These are obtained using a numerical direct model which describes the signal propagation in the branched network. The GA is used to reduce the differences between the measured responses and the simulated responses given by the direct model. The numerical and experimental results provided at the end of the paper confirm the performance of both approaches (MCTDR-NN & MCTDR-GA) in merging data between reflectometers and in eliminating diagnosis ambiguities.