Intelligent detection and identification in fiber-optical perimeter intrusion monitoring system based on the FBG sensor network

Wu, Huijuan; Qian, Ya; Zhang, Wei; Li, Hanyu; Xie, Xin

doi:10.1007/s13320-015-0274-8

Cited by 28 publications

(6 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our results agree with the hypotheses of Wu et al 2015 andFriedli et al 2019 , who observed DAS response changing over time, suggesting that the coupling between the fiber optic cable and the host medium may change due to aging and seasonal environmental changes. For impact source locations offset from the fiber optic cable array, the impactgenerated seismic wave would travel from the ground surface of the undisturbed native silty sand material towards the trench material containing the fiber optic cable.…”

Section: Soil Moisture and Temperaturesupporting

confidence: 92%

See 1 more Smart Citation

Geotechnical effects on fiber optic distributed acoustic sensing performance

Quinn¹

2021

View full text Add to dashboard Cite

Distributed Acoustic Sensing (DAS) is a fiber optic sensing system that is used for vibration monitoring. At a minimum, DAS is composed of a fiber optic cable and an optic analyzer called an interrogator. The oil and gas industry has used DAS for over a decade to monitor infrastructure such as pipelines for leaks, and in recent years changes in DAS performance over time have been observed for DAS arrays that are buried in the ground. This dissertation investigates the effect that soil type, soil temperature, soil moisture, time in-situ, and vehicle loading have on DAS performance for fiber optic cables buried in soil. This was accomplished through a field testing program involving two newly installed DAS arrays. For the first installation, a new portion of DAS array was added to an existing DAS array installed a decade prior. The new portion of the DAS array was installed in four different soil types: native fill, sand, gravel, and an excavatable flowable fill. Soil moisture and temperature sensors were buried adjacent to the fiber optic cable to monitor seasonal environmental changes over time. Periodic impact testing was performed at set locations along the DAS array for over one year. A second, temporary DAS array was installed to test the effect of vehicle loading on DAS performance. Signal to Noise Ratio (SNR) of the DAS response was used for all the tests to evaluate the system performance. The results of the impact testing program indicated that the portions of the array in gravel performed more consistently over time. Changes in soil moisture or soil temperature did not appear to affect DAS performance. The results also indicated that time DAS performance does change somewhat over time. Performance variance increased in new portions of array in all material types through time. The SNR in portions of the DAS array in native silty sand material dropped slightly, while the SNR in portions of the array in sand fill and flowable fill material decreased significantly over time. This significant change in performance occurred while testing halted from March 2020 to August 2020 due to the Covid-19 pandemic. These significant changes in performance were observed in the new portion of test bed, while the performance of the prior installation remained consistent. It may be that, after some time in-situ, SNR in a DAS array will reach a steady state. Though it is unfortunate that testing was on pause while changes in DAS performance developed, the observed changes emphasize the potential of DAS to be used for infrastructure change-detection monitoring. In the temporary test bed, increasing vehicle loads were observed to increase DAS performance, although there was considerable variability in the measured SNR. The significant variation in DAS response is likely due to various industrial activities on-site and some disturbance to the array while on-boarding and off-boarding vehicles. The results of this experiment indicated that the presence of load on less than 10% of an array channel length may improve DAS performance. Overall, this dissertation provides guidance that can help inform the civil engineering community with respect to installation design recommendations related to DAS used for infrastructure monitoring.

show abstract

Section: Soil Moisture and Temperaturesupporting

confidence: 92%

“…Vibrations induced by activity near the installed DAS induce submicroscopic changes in the fiber length, core refractive index, and core diameters (Liu et al 2016). DAS can be trained to identify an activity of interest (Madsen et al 2008, Wu et al 2015, and Friedli et al 2019…”

Section: Geotechnical Subsurface Investigationsmentioning

confidence: 99%

Geotechnical effects on fiber optic distributed acoustic sensing performance

Quinn¹

2021

View full text Add to dashboard Cite

show abstract

“…In the experiment, the average recognition rate of five sample signals was as high as 96.67%, achieving a very high accuracy. 20) It can be seen that the use of machine learning related algorithms in data processing of optical fiber sensor systems would be far superior to traditional computational methods, greatly improving the convenience and accuracy.…”

Section: Introductionmentioning

confidence: 99%

Development of optical fiber strain sensor system based on machine learning and polarization

Zhao,

Duan,

Yuan

2024

Jpn. J. Appl. Phys.

View full text Add to dashboard Cite

Based on the principle that the polarization state of light propagating in a single-mode fiber changes with external strains, an optical fiber sensor system based on machine learning and polarization for multi-point strain measurement is proposed. To address the influence of the front sensor on the rear sensor and to minimize interference from unrelated inputs, we have employed a data processing method that constructs an individual neural network model for each sensor. This approach uses the polarization state of the reflected light of the sensors as the neural networks’ input and the sensors’ rotation angles as the output, training the designed neural networks for learning. The trained neural networks produce predicted outputs that demonstrate high consistency with the experimental data, achieving an average prediction accuracy of 99% on test data. These results validate the effectiveness of our sensor system and data processing method.

show abstract

“…The classification of intrusion signals has been a topic of interest among researchers in perimeter security. Wu et al applied principal component analysis to extract features and identify events using a k-nearest neighbor classifier [7]. However, the limited dataset used in their study may limit the generalizability of their approach, making it potentially unsuitable for substation perimeter intrusion systems.…”

Section: Introductionmentioning

confidence: 99%

Research on substation intrusion event identification method based on MTF and CNN

Shao,

Jiang,

Jiang

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

This research provides a detection approach based on Markov transition field (MTF) and convolutional neural network (CNN) for substation perimeter intrusion event recognition. Because of the complexity and variety of external signals, which makes sensor detection more challenging, determining and analyzing the intrusion behavior of vibration signals induced by intrusion has become critical to improving the identification rate of intrusion-like occurrences. The obtained one-dimensional signals are mapped into two-dimensional pictures using MTF to reflect better the properties of intrusion-like signals, which can yield deeper signal details than the usual feature extraction approach. The CNN-vgg19 model’s excellent image feature identification capabilities are utilized to detect and categorize the acquired 2D feature pictures. The experimental results show that the average recognition rate of the six intrusion events is 96.7%, and the average recognition rate of the noise events is 99%, which can effectively identify the noise events and reduce the false-positive rate. The study’s findings are valuable for substation and peripheral security intrusion products.

show abstract

Intelligent detection and identification in fiber-optical perimeter intrusion monitoring system based on the FBG sensor network

Cited by 28 publications

References 23 publications

Geotechnical effects on fiber optic distributed acoustic sensing performance

Geotechnical effects on fiber optic distributed acoustic sensing performance

Development of optical fiber strain sensor system based on machine learning and polarization

Research on substation intrusion event identification method based on MTF and CNN

Contact Info

Product

Resources

About