Online external intrusion monitoring method based on heterogeneous distributed optical fiber sensor

Abstract

The invention discloses an online external intrusion monitoring method based on a heterogeneous distributed optical fiber sensor, and belongs to the field of data-driven fault diagnosis. The method comprises the following steps: (1) designing an LGSSN; classifying signals of each sensor node i in real time by a local classifier to obtain a local classification result; (2) designing a local classifier based on a deep isolated forest algorithm constructed by a deep auto-encoder and an isolated forest, and describing local characteristics of each sensor node i; (3) introducing a weight half-sharing strategy to simplify an LGSSN structure, and designing a parallel computing framework; (4) designing a GIM based on Bayesian reasoning; and judging whether intrusion exists in the monitoring area and the intrusion position when intrusion exists in combination with the space sliding window. Based on the optical fiber vibration signals, the problem of intelligent intrusion monitoring of heterogeneous distributed sensors under the condition of extremely unbalanced high-dimensional samples is solved.

Description

technical field [0001] The invention belongs to the field of data-driven fault diagnosis, in particular to an online intrusion monitoring method based on heterogeneous distributed optical fiber sensors. Background technique [0002] With the continuous in-depth development of Internet technology, a new generation of network technology, the Internet of Things, has been formed based on the Internet; it was first proposed at the International Conference on Mobile Computers and Networks held in the United States in 1999, and was held in Tunisia in 2005. At the World Summit on the Information Society, the International Telecommunication Union (ITU) released the "ITU Internet Report 2005: Internet of Things" which formally proposed the concept of the Internet of Things. Until now, the Internet of Things has been widely used in many fields such as intelligent transportation, environmental protection, government work, public safety, safe home, intelligent fire protection, and indust...

AI Technical Summary

Problems solved by technology

[0006] In order to solve the problems of performance degradation caused by heterogeneous signals and low engineering feasibility caused by the need for a large amount of labeled data in the application of online intrusion monitoring based on heterogeneous distributed optical fiber sensors in the prior art, the present invention provides a heterogeneous On-line intrusion monitoring method based on distributed optical fiber sensor

Images