Figure 3 - uploaded by Christoph Wiesmeyr
Content may be subject to copyright.
Leading and trailing edge of the object in blue and orange, respectively, plotted over the vibration detection results in black and white; note that the depicted signal consists of the first 35 s of the signal shown in Figure 2.
Source publication
In the context of railway safety, it is crucial to know the positions of all trains moving along the infrastructure. In this contribution, we present an algorithm that extracts the positions of moving trains for a given point in time from Distributed Acoustic Sensing (DAS) signals. These signals are obtained by injecting light pulses into an optica...
Context in source publication
Context 1
... illustration of the vibration detection can be found in Figure 2. The first step of the tracking algorithm is the edge detection. In Figure 3, we give an example of the result of the edge detection from the first 35 s of the dataset shown in Figure 2. After the edge detection, the assignment and Kalman filtering are performed. ...
Similar publications
The safety and comfort of high-speed trains raises the strict demands on the performance of the track subgrade system during the service life over 100 years, for example, strict post-construction settlement at millimeter level, appropriate dynamic stiffness, and long-term durability. Under extreme climatic conditions such as heavy rainfall, persist...
This article is based on the history of British railway reform, combined with related theories and policies, and explored what kind of regulatory policies should be adopted in what kind of economic environment.
Citations
... DAS has the capabilities to be a useful measurement device for any applications that require many distributed sensing elements across long distances. For example, real-time tracking of train and wagon locations on a railway only requiring a fibre to be non-intrusively added along the train track [137]. DAS has also started to be used for power cable monitoring for detection of failures or damages produced by mechanical impacts [138] across their lengths. ...
The performance and reliability of high voltage systems are critical for power generation and distribution, allowing power to continue flowing for everyday life.
Partial discharge is both a cause and important indicator of damage developing within electrical insulation. By monitoring partial discharge activity during an electrical asset's lifetime, an assessment of the insulation condition can be made and used to inform decisions about repairs or replacement.
Most existing methods for partial discharge detection are only able to cover either a single device or short distance, requiring many discrete sensors for total coverage.
Distributed acoustic sensing is already used widely in other commercial areas for geophysics and seismic data acquisition. However, it has been dismissed for detection of partial discharge due to low sample rates in comparison to the frequency of acoustic emissions from partial discharges.
This thesis demonstrates through aliasing mechanisms, that detection of these high-frequency acoustic emissions can be downsampled and identified.
This thesis reports report fibre-optic based distributed acoustic sensing for detection and measurement of partial discharge providing a continuous detection region of 5km with inherent positional information within 1.25m.
The acoustic-strain interaction on the fibre optic, including the surrounding acoustic environment, is modelled demonstrating significant ringing due to reverberations of the initial impulse, as well as demonstrating an important aliasing method permitting the detection of much higher frequency signals than the original sampling rate.
Laboratory partial discharge sources of both void and treeing varieties were manufactured and used to demonstrate this detection experimentally, covering a range of partial discharge sizes and sensor placements.
This work also includes development of an alternative synchronisation method to allow for detailed sample-for-sample comparisons between different electrical, acoustic and distributed acoustic sensing measurements; each with different data types and sample rates.
... Therefore, DAS can be tailored for monitoring linear infrastructures in complex and harsh environments. In recent years, researchers and practitioners worldwide have carried out a large number of field investigations on linear infrastructures using DAS, such as pipeline leakage monitoring [33,34] and rail track health monitoring [35,36]. Figure 1 briefly shows some current and potential application scenarios of DAS for monitoring linear infrastructures and related geohazards. ...
... However, utilizing DAS for train positioning and speed monitoring also faces some challenges; for instance, how to bury sensing cables near tracks without affecting railway transportation and how to quickly extract effective information from continuous monitoring data. To process sensing data accurately and quickly, a variety of intelligent algorithms have been developed [36,51,52]. He et al. proposed an improved Canny algorithm for precise train positioning and the feasibility of this algorithm has been verified through field experiments [52]. ...
... The same authors also proposed a cubical smoothing algorithm with a five-point approximation to denoise vibration signals and shorten the calculation time. Wiesmeyr et al. proposed a real-time train tracking algorithm that runs on the basis of 1 s signals without delay [36]. This algorithm combines machine learning techniques, such as principal component analysis (PCA) and support vector machines (SVMs), with image processing methods, such as edge monitoring and Kalman filtering. ...
Linear infrastructures, such as railways, tunnels, and pipelines, play essential roles in economic and social development worldwide. However, under the influence of geohazards, earthquakes, and human activities, linear infrastructures face the potential risk of damage and may not function properly. Current monitoring systems for linear infrastructures are mainly based on non-contact detection (InSAR, UAV, GNSS, etc.) and geotechnical instrumentation (extensometers, inclinometers, tiltmeters, piezometers, etc.) techniques. Regarding monitoring sensitivity, frequency, and coverage, most of these methods have some shortcomings, which make it difficult to perform the accurate, real-time, and comprehensive monitoring of linear infrastructures. Distributed acoustic sensing (DAS) is an emerging sensing technology that has rapidly developed in recent years. Due to its unique advantages in long-distance, high-density, and real-time monitoring, DAS arrays have shown broad application prospects in many fields, such as oil and gas exploration, seismic observation, and subsurface imaging. In the field of linear infrastructure monitoring, DAS has gradually attracted the attention of researchers and practitioners. In this paper, recent research and the development activities of applying DAS to monitor different types of linear infrastructures are critically reviewed. The sensing principles are briefly introduced, as well as the main features. This is followed by a summary of recent case studies and some critical problems associated with the implementation of DAS monitoring systems in the field. Finally, the challenges and future trends of this research area are presented.
... Another advantage of DAS is in its convenient mode of deployment, whereby, widespread existing telecommunication cables can be utilized as dense array sensors, especially in highlybuilt cities (Lindsey et al., 2020;Song et al., 2021). It is worth noting that urban-scale DAS applications are not limited to vehicle traffic monitoring (Chambers, 2020;van den Ende et al., 2021) and interferometry studies (Dou et al., 2017;Song et al., 2021), but other moving sources like subways (Ferguson et al., 2020) and railway trains (Cedilnik et al., 2018;Wiesmeyr et al., 2020). The trackside cables connected to an interrogator can provide researchers with the opportunity to record traininduced signals, and monitor the location and speed of trains, towards enhancing the train control system. ...
... Trackside DAS recordings require a lot of man-hour inspection/observation to extract the locations of moving trains; this necessitates the need to develop automatic methods for monitoring railway traffic using the high-volume original waveform data. Given that the train-induced signals are spatially continuous, and leave data "footprints" as linear features in the DAS recordings, the Kalman filter has been suggested to be an effective approach to extracting the tracks of individual trains (Wiesmeyr et al., 2020), yet the method may not achieve stable track predictions when it comes to significant speed variant cases. In addition, the method may not accurately extract/predict the locations from cross superimposed signals (Iswanto and Li, 2017), which could be the case when two trains from opposite directions move and pass each other. ...
... Such computational performance implies that our method is suitable for near real-time railway traffic monitoring. In addition, the Kalman filter is another approach to smooth the train trajectories (Ferguson et al., 2020;Wiesmeyr et al., 2020), and it would be interesting to test extended and adaptive Kalman filters (Terejanu, 2008;Vullings et al., 2010) on arrival picks and the detection results beamformed by subarrays. We could delve deeper into this in the future work. ...
The importance of railway safety cannot be overemphasized; hence it requires reliable traffic monitoring systems. Widespread trackside telecommunication fiber-optic cables can be suitably deployed in the form of dense vibration sensors using Distributed Acoustic Sensing technology (DAS). Train-induced ground motion signals are recorded as continuous “footprints” in the DAS recordings. As the DAS system records huge datasets, it is thus imperative to develop optimized/stable algorithms which can be used for accurate tracking of train position, speed, and the number of trains traversing the position of the DAS system. In this study, we transform a 6-days continuous DAS data sensed by a 2-km cable into time-velocity domain using beamforming on phase-squeezed signals and automatically extract the position and velocity information from the time-beampower curve. The results are manually checked and the types of the trains are identified by counting the peaks of the signals. By reducing the array aperture and moving subarrays, the train speed-curve/motion track is obtained with acceptable computational performance. Therefore, the efficiency and robustness of our approach, to continuously collect data, can play a supplementary role with conventional periodic and time-discrete monitoring systems, for instance, magnetic beacons, in railway traffic monitoring. In addition, our method can also be used to automatically slice time windows containing train-induced signals for seismic interferometry.
... As a state-of-art vibration sensor, distributed acoustic sensing (DAS) has developed rapidly in the field of earth science and engineering (Parker et al., 2014;Soga and Luo, 2018;Lindsey et al., 2020;Fang et al., 2020;Lindsey and Martin, 2021). Benefiting from its capability of producing dense and distributed measurements with kilohertz time sampling and at submeter channel spacing along kilometers of optical fiber, DAS has opened up many possibilities in tackling the limitation of the conventional seismic sensor for in-tunnel monitoring, including construction event recognition (Zhang et al., 2021), tunnel structure monitoring (Hu et al., 2021), and train tracking (Wiesmeyr et al., 2020). We implement a DAS system in a TBM tunnel under construction for tunnel monitoring. ...
... In 2020, Christoph et al. proposed a real-time train tracking algorithm. The performance was tested in tunnels with standard cable trenches and on open tracks with directly connected cables [99] (Figure 29). The study provided a new idea for train positioning. ...
... (b) Train detection result for a train on test site 2; the green boxes indicate coupled cable segments; the background without the train shows increased noise. (c) False positive train track due to false positive vibration detection[99]. ...
Distributed acoustic sensing techniques based on Rayleigh scattering have been widely used in many applications due to their unique advantages, such as long-distance detection, high spatial resolution, and wide sensing bandwidth. In this paper, we provide a review of the recent advancements in distributed acoustic sensing techniques. The research progress and operation principles are systematically reviewed. The pivotal technologies and solutions applied to distributed acoustic sensing are introduced in terms of polarization fading, coherent fading, spatial resolution, frequency response, signal-to-noise ratio, and sensing distance. The applications of the distributed acoustic sensing are covered, including perimeter security, earthquake monitoring, energy exploration, underwater positioning, and railway monitoring. The potential developments of the distributed acoustic sensing techniques are also discussed.
... The energy of ambient noise was concentrated between 5 and 25 Hz to calculate noise cross-correlation functions, which falls into the typical traffic noise frequency band. When considering rail-vehicle detection directly, the research presented in [29] shows concept on settings real-time train tracking from distributed acoustic sensing data. Authors present an algorithm that extracts the positions of moving trains for a given point in time from vibration signals. ...
The purpose of this research paper is to present the application of the developed sound method as a supporting tool to deal with railway traffic flow control. It is found that controlling railway line occupancy is the main issue associated with railway traffic flow. For this purpose, the line occupancy control based on a sound method has been developed. The concept of using sound waves as a source of information about approaching people, animals, vehicles, etc., has been known for centuries, and is due to the natural properties of the sense of hearing. There are many engineering attempts on the use of this phenomenon, which are mostly based on applications of distributed fiber-optic sensing technology. This paper presents the results of the sound pressure measurement in the immediate proximity of the rail to analyze and evaluate the use of the acoustic wave as an information carrier on approaching rail vehicles. The purpose of this research is to discuss the sound method introduced here, and apply it in different circumstances.
... Distributed acoustic sensing system is a recent technology that continues to demonstrate its effectiveness for railway environments monitoring. In fact, DAS has been deployed for railway monitoring [1,2,6,7,8,10] and other purposes [4,5,6,9]. This technology is attracting more attention especially with the continuing deployment of optical fiber cables along the rails for telecommunications purposes. ...
The interest of Distributed Acoustic Sensing systems (DAS) is growing in industry. However, its application in the railway field remains a novelty. At the same time, the different machine-learning approaches have proven their good performance in different fields and applications. Combining these two technologies could solve complex problems. We present in this work a solution that uses a machine learning method to analyse data sensed by a DAS system for automatic railway network monitoring. The signals received are pre-processed and then a thresholding is applied to detect and locate potential events. The detected events are then analysed and recognized by a supervised machine learning model which predicts whether the event corresponds to a train or not. As soon as a train is recognized, a tracking algorithm is launched to track it. We periodically predict the average speed and the length of the tracked train. The system is deployed and tested for near real-time train localization and tracking in tunnels. We obtained very good results achieving +97% of accuracy for the train recognition model and very precise tracking results. Our contribution can be adapted and extended for the detection of other railway events such as intrusion detection, broken rails, rocks falling on the tracks, etc.
... Distributed acoustic sensing system is a recent technology that continues to demonstrate its effectiveness for railway environments monitoring. In fact, DAS has been deployed for railway monitoring [1,2,6,7,8,10] and other purposes [4,5,6,9]. This technology is attracting more attention especially with the continuing deployment of optical fiber cables along the rails for telecommunications purposes. ...
The interest of Distributed Acoustic Sensing systems (DAS) is growing in industry. However, its application in the railway field remains a novelty. At the same time, the different machine-learning approaches have proven their good performance in different fields and applications. Combining these two technologies could solve complex problems. We present in this work a solution that uses a machine learning method to analyse data sensed by a DAS system for automatic railway network monitoring. The signals received are pre-processed and then a thresholding is applied to detect and locate potential events. The detected events are then analysed and recognized by a supervised machine learning model which predicts whether the event corresponds to a train or not. As soon as a train is recognized, a tracking algorithm is launched to track it. We periodically predict the average speed and the length of the tracked train. The system is deployed and tested for near real-time train localization and tracking in tunnels. We obtained very good results achieving +97% of accuracy for the train recognition model and very precise tracking results. Our contribution can be adapted and extended for the detection of other railway events such as intrusion detection, broken rails, rocks falling on the tracks, etc.
... Properly warped content, according to the depth profile, is projected onto the tunnel wall at runtime inside a tunnel. To locate the train in a tunnel, a combination of an odometer and various sensors that may be installed on the train [8,43] or near the rail [2,45] are some possible options. However, we intentionally avoid the use of these approaches to make our system independent of any specific subway environment. ...
In this study, we present the first actual working system that can project content onto a tunnel wall from a moving subway train so that passengers can enjoy the display of digital content through a train window. Our stand-alone system can be easily deployed to existing trains because it does not assume any specific type of interface requiring data transfer with the train. To effectively estimate the position of the train in a tunnel, we propose counting sleepers, which are installed at regular interval along the railway, using a distance sensor. In the preprocessing step, the side depth variation along the tunnel is stored in synchronization with the train location in a tunnel profile. The tunnel profile is constructed using pointclouds captured by a depth camera installed next to the projector. The tunnel profile is used to identify projectable sections that will not contain too much interference by possible occluders. The tunnel profile is also used to retrieve the depth at a specific location so that a properly warped content can be projected for viewing by passengers through the window when the train is moving at runtime. Here, we show that the proposed system can operate on an actual train and evaluate the quality of the projection results through simulation.
... The SVM achieved an average identification rate of 92.62%, intrusion detection rate of up to 98.6%, and event classification rate of 91.2%. The SVM classifier was also employed in a paper [73] by Wiesmeyr et al. to monitor and extract active positions of a train with a 40 km long fiber optic cable. In this case, a FFT was used for signal processing and principle component analysis (PCA) was used to remove dimensionality from 10 feature values to 2 feature values. ...
The phase sensitive optical time-domain reflectometer (ϕ-OTDR), or in some applications called distributed acoustic sensing (DAS), has been a popularly used technology for long-distance monitoring of vibrational signals in recent years. Since ϕ-OTDR systems usually operate in complicated and dynamic environments, there have been multiple intrusion event signals and also numerous noise interferences, which have been a major stumbling block toward the system's efficiency and effectiveness. Many studies have proposed different techniques to mitigate this problem mainly in ϕ-OTDR setup upgrades and improvements in data processing techniques. Most recently, machine learning methods for event classifications in order to help identify and categorize intrusion events have become the heated spot. In this paper, we provide a review of recent technologies from conventional machine learning algorithms to deep neural networks for event classifications aimed at increasing the recognition/classification accuracy and reducing nuisance alarm rates (NARs) in ϕ-OTDR systems. We present a comparative analysis of the current classification methods and then evaluate their performance in terms of classification accuracy, NAR, precision, recall, identification time, and other parameters.
