Ensemble Learning with Stochastic Configuration Network for Noisy Optical Fiber Vibration Signal Recognition.

Hongquan Qu,Yanping Wang,Tingliang Feng,Yuan Zhang

doi:10.3390/s19153293

Hongquan Qu, Yanping Wang + Show 2 more

Open Access

https://doi.org/10.3390/s19153293

Copy DOI

Abstract

Optical fiber pre-warning systems (OFPS) based on Φ-OTDR are applied to many different scenarios such as oil and gas pipeline protection. The recognition of fiber vibration signals is one of the most important parts of this system. According to the characteristics of small sample set, we choose stochastic configuration network (SCN) for recognition. However, due to the interference of environmental and mechanical noise, the recognition effect of vibration signals will be affected. In order to study the effect of noise on signal recognition performance, we recognize noisy optical fiber vibration signals, which superimposed analog white Gaussian noise, white uniform noise, Rayleigh distributed noise, and exponentially distributed noise. Meanwhile, bootstrap sampling (bagging) and AdaBoost ensemble learning methods are combined with original SCN, and Bootstrap-SCN, AdaBoost-SCN, and AdaBoost-Bootstrap-SCN are proposed and compared for noisy signals recognition. Results show that: (1) the recognition rates of two classifiers combined with AdaBoost are higher than the other two methods over the entire noise range; (2) the recognition for noisy signals of AdaBoost-Bootstrap-SCN is better than other methods in recognition of noisy signals.

Highlights

At present, inflammable and explosive resources such as oil and natural gas are mainly transported through pipelines, which is convenient and fast
In the recognition of noisy fiber vibration signals with a small sample set, the problem of low classification accuracy still occurs in the use of stochastic configuration network (SCN), and the recognition rate is sometimes even lower than 50%
AdaBoost-SCN and AdaBoost-Bootstrap-SCN are greater than 0.95, which indicates that the use improve thecan recognition the vibrationrate signal thevibration case of noiseless superposition noisy

Summary

Introduction

Inflammable and explosive resources such as oil and natural gas are mainly transported through pipelines, which is convenient and fast. Problems such as resource waste and environmental pollution caused by pipeline leakage exist. The phase-sensitive optical time-domain reflectometer (Φ-OTDR) is a reflection method, which can be used to detect concurrent vibration signals. Compared with other monitoring methods, optical fiber pre-warning systems (OFPS) based on Φ-OTDR are a very common method of long-distance detection and security protection due to their advantage in design (anti-interference, small additional damage, easy upgrade of back-end, low energy consumption in the field and suitable for long-distance defense) [6]

Methods

Findings

Discussion

Conclusion