Physics-informed network paradigm with data generation and background noise removal for diverse distributed acoustic sensing applications

TL;DR

This paper introduces a physics-informed neural network paradigm for DAS that generates training data and removes background noise, enabling effective event recognition without relying on real-world event data.

Contribution

It presents a novel physics-based training approach for DAS neural networks that eliminates the need for real-world event data and enhances noise removal capabilities.

Findings

Achieved 91.8% fault diagnosis accuracy in belt conveyor monitoring.

Demonstrated generalization across different sites and applications.

Performed comparably or better than data-driven models trained with real data.

Abstract

Distributed acoustic sensing (DAS) has attracted considerable attention across various fields and artificial intelligence (AI) technology plays an important role in DAS applications to realize event recognition and denoising. Existing AI models require real-world data (RWD), whether labeled or not, for training, which is contradictory to the fact of limited available event data in real-world scenarios. Here, a physics-informed DAS neural network paradigm is proposed, which does not need real-world events data for training. By physically modeling target events and the constraints of real world and DAS system, physical functions are derived to train a generative network for generation of DAS events data. DAS debackground net is trained by using the generated DAS events data to eliminate background noise in DAS data. The effectiveness of the proposed paradigm is verified in event identification application based on a public dataset of DAS spatiotemporal data and in belt conveyor fault monitoring application based on DAS time-frequency data, and achieved comparable or better performance than data-driven networks trained with RWD. Owing to the introduction of physical information and capability of background noise removal, the paradigm demonstrates generalization in same application on different sites. A fault diagnosis accuracy of 91.8% is achieved in belt conveyor field with networks which transferred from simulation test site without any fault events data of test site and field for training. The proposed paradigm is a prospective solution to address significant obstacles of data acquisition and intense noise in practical DAS applications and explore more potential fields for DAS.