A Hybrid Model Integrating MPSE and IGNN for Events Recognition Along Submarine Cables

The vibration signal is essential for accurate event recognition along submarine cables. However, rapid and concise identification still poses challenges for prompt recognition and classification of events in harsh environments. For such reasons, this article proposes a developed hybrid model combining the modern power spectrum estimation (MPSE) and improved gradient neural networks (IGNNs), to identify and organize events instantaneously. Three different categories of data are selected as data samples, collected using the phase-sensitive optical time-domain reflectometry (Phi-OTDR) device. The signal characteristics of the power distribution are extracted in the frequency and time domains. These characteristics together form the eigenvector, used in a multiclass IGNN classifier, to initiate the extent and position of collision events on the cable. The results demonstrate that the proposed hybrid model has a better identification rate, compared to the existing schemes used for the same purposes. It is verified that the accuracy rate of identification has expanded by almost 1%; confirming the validity and reliability of the proposed hybrid model.

Automated summary

This article proposes a developed hybrid model combining modern power spectrum estimation and improved gradient neural networks, to accurately identify and organize events along submarine cables. Signal characteristics are extracted in the frequency and time domains, and a multiclass IGNN classifier is used to determine the extent and position of collision events on the cable, resulting in real-time recognition and classification.