A machine learning method for inclinometer lateral deflection calculation based on distributed strain sensing technology
- PDF / 8,089,606 Bytes
- 19 Pages / 595.276 x 790.866 pts Page_size
- 86 Downloads / 165 Views
ORIGINAL PAPER
A machine learning method for inclinometer lateral deflection calculation based on distributed strain sensing technology Lei Zhang 1 & Bin Shi 1 & Honghu Zhu 1 & Xiong Yu 2 & Guangqing Wei 3 Received: 10 September 2019 / Accepted: 14 February 2020 # Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract Due to its unique advantages, the distributed fiber optical sensing (DFOS) technology has been used to study the performance of inclinometer so as to monitor landslide deformation. Strain distribution of inclinometer can be obtained by distributed strain sensing (DSS) cables, and the strain-deflection relationship can be established by using the widely accepted methods (e.g., the quadratic integral method and classical conjugate beam method). However, the application of quadratic integral method and classical conjugate beam method are based on many assumptions, and there will be remarkable deviation between calculated deflection and actual displacement with the increase of integral length. Given this, a new deflection calculation method based on machine learning is proposed. Through learning on the monitoring data, an implicit function model between depth, strain, and measured displacement is established by using the BP (back propagation) neural network algorithm. The efficiency of the proposed model has been verified against measured displacement, which demonstrates the capability of this method for landslide deformation prediction. Compared with the traditional integral method, the lateral deflection curve of inclinometer calculated by the proposed method is closer to the actual measured displacement both in trend and values. The proposed model shows great potential in the application of deflection calculation in engineering. Keywords Machine learning . Deflection calculation . BOTDR . Fiber optic sensing cable
Introduction Landslides, as one of the most common natural hazards, are widespread all over the world. This kind of disaster poses a great threat to the safety of people’s lives and property (Aleotti and Chowdhury 1999; Wieczorek and Leahy 2008; Petley 2012; Wolter et al. 2014). The inclinometers are widely used to monitor landslide deformation, which help indicate the development of sliding surfaces and understand the stability condition of landslides (Stark and Choi 2008; Massey et al. * Bin Shi [email protected] * Honghu Zhu [email protected] 1
School of Earth Sciences and Engineering, Nanjing University, Nanjing 210023, China
2
Department of Civil Engineering, Case Western Reserve University, Cleveland, OH 44106, USA
3
Suzhou NanZee Sensing Technology Co. Ltd, Suzhou 215123, China
2013). However, traditional inclinometers need manual measurement at each depth which has low efficiency and provide only local data with the risk of missing critical points (Damiano et al. 2017). In addition, when the inclinometer is subject to large deformation, the inclinometer probe cannot be lowered down deeply into a borehole to record displacement. Due to existing problems, the applicat
Data Loading...
