Advances in fibre optic based geotechnical monitoring systems for underground excavations

Quantifying structural status and locating structural anomalies are critical to tracking and safeguarding the safety of long-distance underground structures. Given the dynamic and distributed monitoring capabilities of an ultra-weak fiber Bragg grating (FBG) array, this paper proposes a method combining the stacked denoising autoencoder (SDAE) network and the improved dynamic time wrapping (DTW) algorithm to quantify the similarity of vibration responses. To obtain the dimensionality reduction features that were conducive to distance measurement, the silhouette coefficient was adopted to evaluate the training efficacy of the SDAE network under different hyperparameter settings. To measure the distance based on the improved DTW algorithm, the one nearest neighbor (1-NN) classifier was utilized to search the best constraint bandwidth. Moreover, the study proposed that the performance of different distance metrics used to quantify similarity can be evaluated through the 1-NN classifier. Based on two one-dimensional time-series datasets from the University of California, Riverside (UCR) archives, the detailed implementation process for similarity measure was illustrated. In terms of feature extraction and distance measure of UCR datasets, the proposed integrated approach of similarity measure showed improved performance over other existing algorithms. Finally, the field-vibration responses of the track bed in the subway detected by the ultra-weak FBG array were collected to determine the similarity characteristics of structural vibration among different monitoring zones. The quantitative results indicated that the proposed method can effectively quantify and distinguish the vibration similarity related to the physical location of structures.

Section: Introductionmentioning

confidence: 99%

Combining SDAE Network with Improved DTW Algorithm for Similarity Measure of Ultra-Weak FBG Vibration Responses in Underground Structures

Zuo

et al. 2020

“…By virtue of these unique advantages of realizing real-time online monitoring and intelligent remote control [ 17 , 18 ], it becomes an optional solution to the intelligent mining construction and has tremendous potential for application in mining engineering [ 19 , 20 ]. The preliminary application of DOFS in mining rock mechanics and ground control research [ 21 , 22 ] already indicated that it realized the accurate capture and distribution monitoring of internal rock stress [ 23 , 24 ]. Moreover, the DOFS technology has the advantages of portable installation, low environmental requirements, large-scale, and dynamic continuous measurement, which are specific to the deformation characteristics of mining-induced overburden study.…”

Section: Introductionmentioning

confidence: 99%

The Characterization Pattern of Overburden Deformation with Distributed Optical Fiber Sensing: An Analogue Model Test and Extensional Analysis

Yuan

Chai

Ren

et al. 2020

The evolution of overburden deformation is crucial for safety and environmental efficiency and its monitoring is becoming a key scientific issue. The use of an optical fiber sensor (OFS) for mining engineering is now receiving praise by virtue of its distinct abilities of distribution, high accuracy, and anti-interference measurement. Nevertheless, the dynamic response of OFS monitoring on overburden deformation still needs to be characterized in detail. This paper analyzed the characterization pattern of overburden deformation based on distributed optical fiber sensing (DOFS) by means of an analogue model test. Then, we discuss the influence of rules of optical fiber embedding on a model test in a numerical simulation. The results show that the DOFS monitoring demonstrates the time-space evolution of overburden deformation and the development of three horizontal areas and three vertical zones. A standardization DOFS characterization model is proposed to expound the characterization mechanism of the overburden structure zoning process; the influence of optical fiber embedding on rock displacement in the model test is revealed, and it is found that the displacement error will increase sharply when the fiber diameter is larger than 2 mm. These findings could provide an effective solution for a monitoring method in intelligent mining from the perspective of a theoretical basis and technological system.

“…For long-distance monitoring needs, especially for subway tunnels, distributed fiber-optic sensing technology has been widely recognized as the most promising means of addressing complex needs due to its advantages of large-scale monitoring, high sensitivity, and multiplexing capabilities [12]. For instance, the safety monitoring of subway structures based on Brillouin optical time domain reflectometry (BOTDR) technology [13] has been reported [14,15]. In addition to BOTDR-based static measurement, distributed fiber-optic sensors for dynamic measurement [16], especially distributed acoustic sensing (DAS) technology [17,18] have been another research hotspot.…”

Section: Introductionmentioning

confidence: 99%

A Novel Monitoring Approach for Train Tracking and Incursion Detection in Underground Structures Based on Ultra-Weak FBG Sensing Array

Nan

Yi-qiang

et al. 2019

Tracking operating trains and identifying illegal intruders are two important and critical issues in subway safety management. One challenge is to find a reliable methodology that would enable these two needs to be addressed with high sensitivity and spatial resolution over a long-distance range. This paper proposes a novel monitoring approach based on distributed vibration, which is suitable for both train tracking and incursion detection. For an actual subway system, ultra-weak fiber Bragg grating (FBG) sensing technology was applied to collect the distributed vibration responses from moving trains and intruders. The monitoring data from the subway operation stage were directly utilized to evaluate the feasibility of the proposed method for tracking trains. Moreover, a field simulation experiment was performed to validate the possibility of detecting human intrusion. The results showed that the diagonal signal pattern in the distributed vibration response can be used to reveal the location and speed of the moving loads (e.g., train and intruders). Other train parameters, such as length and the number of compartments, can also be obtained from the vibration responses through cross-correlation and envelope processing. Experimental results in the time and frequency domains within the selected intrusion range indicated that the proposed method can distinguish designed intrusion cases in terms of strength and mode.