Quasi-distributed Monitoring Research Articles

Seismic response prediction method of train-bridge coupled system based on convolutional neural network-bidirectional long short-term memory-attention modeling

Seismic response prediction is crucial for the safety analysis of train-bridge coupled systems. However, due to the complexity, suddenness, and high-risk nature of earthquakes, there are strong nonlinear relationships among different parts of bridges, making it challenging to express their spatial correlations using analytical models and traditional neural networks. To address this, this paper establishes a ballast track shaker scaling model and employs the grating monitoring measurement method to construct a spatial quasi-distributed monitoring system for the ballast track, thereby collecting seismic strain responses of the train-bridge coupled system under various seismic conditions. A hybrid neural network method is proposed for predicting the seismic responses of the train-bridge coupled system. This hybrid neural network integrates the features of a Convolutional Neural Network (CNN), Bidirectional Long Short-Term Memory Neural Network (BiLSTM), and the attention mechanism, thereby termed the CNN-BiLSTM-attention hybrid neural network. The model was validated using strain responses from 54 seismic scenarios. The results indicate that the model has a Mean Absolute Error (MAE) of 0.2349 and a coefficient of determination (R2) of 0.9446. Comparing the prediction results with those from RNN and LSTM models, it was found that the CNN effectively extracts features under various seismic parameters, while the BiLSTM better captures the temporal information of the strain responses, ensuring effective prediction regardless of the magnitude of strain responses. Therefore, the CNN-BiLSTM-attention hybrid neural network model is recommended for predicting seismic response.

Study on the Quasi-Distributed Monitoring Method of Earth Pressure Based on the Thermomechanical Coupling

Study on the Quasi-Distributed Monitoring Method of Earth Pressure Based on the Thermomechanical Coupling

Strain and vibration measurements by FBG sensors for engineering applications

Fiber optic sensors based on the fiber Bragg grating (FBG) technology [1] is widely used to produce quasi-distributed monitoring systems to measure mechanical parameters for Structural Health Monitoring (SHM) of civil engineering structures [2]. FBG sensors are produced in the core of the optical fiber, as a short segment of fiber where a diffraction grating is produced (5–10 mm). The principle of operation of the FBGs is based on the diffraction occurring at the grating: if broadband light propagates, a quasi-monochromatic counter propagating light originates. The wavelength of the diffracted light depends on the value of the refraction index of the core along the grating which in turn is affected by both temperature and strain. Thus, by measuring the wavelength change of the counter propagating light, the change of strain and the temperature can be worked out. The PREFOS Project [3] aims to develop a novel procedure to apply the use of FBGs to monitor the prestressed strands of civil engineering prefabricated components. In this paper, we report results of an experimental campaign intended to measure the sensitivity of saddle-like sensors to induced vibration and mechanical strain. Measurements were done performing static and dynamic tests on a steel strand equipped with 3 sensors. The tests have been performed applying different tensioning to the steel strand. Static measurements were worked out applying a stepwise tensioning increase. Dynamic tests were worked out at each stepped tension level, inducing vibration by both sharp hammer impact and release of hanged weight. The paper is organized as follows, in section 1 a general description of the testbed structure used for the experiments will be provided. In section 2 the results of static analysis and dynamic tests will be presented with the dynamic behavior of the strand evaluated by performing a simple Fast Fourier Transform (FFT). Finally, the conclusions will be drawn.

Artificial intelligence-based fiber optic sensing for soil moisture measurement with different cover conditions

Actively heated fiber Bragg grating (AH-FBG) can perform quasi-distributed monitoring of soil water content. However, the analysis method needs to be improved to minimize measuring errors. In this study, the artificial intelligence method is proposed and a model test was used to verify its feasibility and to explore the influence of cover conditions. Three cover layers were considered, including bare soil (S), grass (G), and biochar mixed soil (B). The water content measurements based on maximum temperature increase have higher accuracy for G, followed by S, and the worst is B. Fluctuation in the heat power and the longitudinal heat transfer are the main sources of errors. Artificial neural network (ANN) models can effectively improve monitoring accuracy. Cover conditions have a significant influence on the measurements by affecting initial ground temperatures and water content gradients. For field monitoring, the cover layer should be considered when analyzing AH-FBG measurements.

Special issue on Distributed and quasi-distributed monitoring of civil infrastructure systems

Special issue on Distributed and quasi-distributed monitoring of civil infrastructure systems

A simple macro-bending loss optical fiber crack sensor for the use over a large displacement range

Abstract An optical fiber crack sensor based on macro-bending loss for detecting the crack opening displacement (COD) is developed in this paper. The sensor incorporates an extremely simple design, light source and detector. The decrease of the light intensity with displacement variation was reported. The verification experiments to the sensing principle were conducted. The sensor shows a response over a wide range of 212.1 and 87.9 mm in shrinkage and elongation, respectively. The response has two distinct nonlinear regions. A slab cracking model was established and random COD conditions were simulated. It is found that the predicted displacements of the sensor are nearly identical to the measured COD, and both relative errors are basically within 10%. Additionally, the sensor can be connected in series on one optical link to realized quasi-distributed monitoring; if crack shrinkage or elongation can be known in advance, the sensor by designed properly has a larger range of 300 mm. This optical fiber crack sensor is characterized by large measurement range, simple design, high flexibility and low economic cost, which shows a promising application in the field of displacement monitoring.

Implementation of a Mobile Platform Based on Fiber Bragg Grating Sensors for Automotive Traffic Monitoring.

Instrumentation techniques, implementation and installation methods are major concerns in today’s distributed and quasi-distributed monitoring applications using fiber optic sensors. Although many successful traffic monitoring experiments have been reported using Fiber Bragg Gratings (FBGs), there has been no standardized solution proposed so far to have FBG seamlessly implemented in roads. In this work, we investigate a mobile platform including FBG sensors that can be positioned on roads for the purpose of vehicle speed measurements. The experimental results prove the efficiency of the proposed platform, providing a perspective toward weigh-in-motion systems.

A quasi-distributed monitoring method for ground settlement using pulse pre-pump Brillouin optical time domain analysis

In geotechnical engineering, it is critical to measure and control ground settlement. A new method is proposed in this work for quasi-distributed ground settlement monitoring. This method is based on the pulse pre-pump Brillouin optical time domain analysis (PPP-BOTDA). The optical fiber is arranged on the monitoring poles through special supports, forming a zigzag pattern. Based on geometric principles, the formulas converting strains in fibers to displacements of supports are derived. Afterwards, the feasibility of the method is verified through laboratory tests. The results show that the proposed method can achieve accuracy within 1 mm. Compared with traditional discrete-point measurement methods, the proposed method can monitor settlement up to 100 points simultaneously with satisfactory precision, facilitating remote and large scale ground settlement monitoring in geotechnical engineering applications.

Self-Referenced Photon Counting OTDR Technique for Quasi-Distributed Fiber Bragg Gratings Sensors

We demonstrate the operating principle of a quasi-distributed monitoring system based on the concatenation of low-reflectance identical fiber Bragg gratings (FBGs) and interrogated by means of a photon counting optical time domain reflectometer (v-OTDR). A filter placed in the path between the FBGs and the photon-counting OTDR impacts the height of the reflection peaks in the OTDR trace as a function of their resonance wavelength, and therefore of the measurand. The proposed technique is very easy and allows interrogating a few tens of sensors in a measurement time that does not exceed a few seconds, whatever the number of sensors.