Infrastructure Monitoring Applications Research Articles

Few-Shot Classification with Meta-Learning for Urban Infrastructure Monitoring Using Distributed Acoustic Sensing.

This paper studies an advanced machine learning method, specifically few-shot classification with meta-learning, applied to distributed acoustic sensing (DAS) data. The study contributes two key aspects: (i) an investigation of different pre-processing methods for DAS data and (ii) the implementation of a neural network model based on meta-learning to learn a representation of the processed data. In the context of urban infrastructure monitoring, we develop a few-shot classification framework that classifies query samples with only a limited number of support samples. The model consists of an embedding network trained on a meta dataset for feature extraction and is followed by a classifier for performing few-shot classification. This research thoroughly explores three types of data pre-processing, that is, decomposed phase, power spectral density, and frequency energy band, as inputs to the neural network. Experimental results show the efficient learning capabilities of the embedding model when working with various pre-processed data, offering a range of pre-processing options. Furthermore, the results demonstrate outstanding few-shot classification performance across a large number of event classes, highlighting the framework's potential for urban infrastructure monitoring applications.

Beyond visual-line-of-sight (BVLOS) drone operations for environmental and infrastructure monitoring: a case study in northwestern Canada

Aerial drones typically operate over small geographic areas (<5 km2), yet environmental and infrastructure monitoring applications often require the collection of data over larger areas. Challenges to drone deployments in areas with people and frequent air traffic include aviation regulations that require missions to adhere to within-visual-line-of-sight (VLOS) conditions, thereby limiting mission extents. The performance and fuel consumption of longer drone missions could justify investment to advance future beyond-VLOS (BVLOS) data acquisitions. This work summarizes airspace deconfliction techniques that allowed testing of BVLOS capabilities in relatively busy airspace in northwestern Canada. Drone missions were conducted with a Griffon SeaHunter, capturing high-resolution imagery covering more than 550 km2 along 6200 km of flight lines, increasing conventional drone data coverage by two orders of magnitude. BVLOS hourly endurance was nearly double that of light aviation mapping aircraft, providing a suitable range for extended monitoring operations (1000–1200 km). Fuel consumption (L/100 km) also differed substantially; SeaHunter used 9%–16% of the fuel consumed by conventional mapping aircraft (84%–91% savings). Finally, we summarize lessons learned to further stimulate BVLOS adoption internationally. Opportunities will arise as BVLOS drones will increasingly be operated within a global context of transitions toward low-carbon emission economies.

An Investigation of CTP Use for Wireless Structural Health Monitoring of Infrastructure

Structural Health Monitoring (SHM) is a very important research domain whereby civil infrastructure is monitored. Using wireless technologies can boost SHM by providing the level of autonomous operation that is essential for these tasks. Wireless routing, with its subset, geographic routing, is an important procedure that needs to be optimised, in order to lead packets to the basestation. Occasionally, routing is susceptible to interference and collisions due to a large number of connected devices. This fact led to cooperative transmission; cooperative networks are the ones that utilise relays to accomplish the transmission of packets; thus, resulting in link quality as well as throughput increase. In this paper, we investigate the Collection Tree Protocol (CTP) to show that it can be cooperative when used in an SHM for civil infrastructure monitoring applications giving a geographical essence to the routing protocol. We do that by exploiting the fact that the CTP’s mechanism uses its tree formation for a node to transmit to the best link quality parents. An example of a cooperative model to show that it may be applied to the protocol is given. Further, Indriya testbed results of direct and cooperative transmissions are given to strengthen the case of this work, with which a scenario where the CTP exhibits better link quality when using a relay is given. A practical addition is suggested, whereby an extra field in the packet struct is proposed, which will provide the CTP with further strength to changing conditions and direct communication loss.

Concurrent Imaging for TerraSAR-X: Wide-Area Imaging Paired With High-Resolution Capabilities

The concurrent imaging technique enables parallel acquisitions with different beams or modes, e.g., a wide area Stripmap mode with a High-Resolution Spotlight mode. Such a concurrent Stripmap/Spotlight imaging technique is investigated for TerraSAR-X. This technique employs a pulse-to-pulse interleaving scheme to acquire two acquisitions-even of disjunctive areas-at the same time, offering products with different resolution and coverage portfolios. This capability is especially interesting for customers interested in an overview of a larger area but at the same time observing an area of interest with higher resolution, e.g., for infrastructure monitoring or reconnaissance applications. The basic concepts, as well as the driving system parameters, are discussed in detail, together with a coverage analysis revealing the high availability rate of the mode combinations on a global scale. A processing approach re-using a substantial part of the existing infrastructure is described and exemplary acquisitions are shown, together with a detailed performance analysis with respect to resolution and ambiguities.

In Situ Blind Calibration of Sensor Networks for Infrastructure Monitoring

The recent development of Internet-of-Things (IoT) technologies has enabled smaller and lower-cost sensor nodes, motivating the deployment of more flexible and scalable sensor networks for infrastructure monitoring applications. However, because these nodes tend to be affected by environmental conditions and aging, they are prone to long-term drift over years of operation; thus, they need to be recalibrated on a regular basis to ensure data accuracy. In this paper, we propose an in situ blind calibration algorithm for infrastructure monitoring sensor networks, which requires neither physical intervention nor the assumption that the sensors are measuring identical ground-truth signals. The algorithm uses a multioutput Gaussian process (MOGP) to model the spatial-temporal distribution of the measurand and drift, thus removing irrelevant short-term fluctuations and decomposing the drift from long-term trends. We evaluate the algorithm on a real-world dataset, and the results show that the proposed method can successfully calibrate a number of drifting sensors more than 20% greater than previous methods while achieving a higher drift estimation accuracy.

Distributed Algorithms for Multiple Path Backbone Discovery in Thick Linear Sensor Networks

Continued advancements in microprocessors, electronics, and communication technology have led to the design and development of sensing devices with increased functionalities, smaller sizes, larger processing, storage, and communication capabilities, and decreased cost. A large number of these sensor nodes are used in many environmental, infrastructure, commercial, and military monitoring applications. Due to the linearity of a good number of the monitored structures such as oil, gas, and water pipelines, borders, rivers, and roads, the wireless sensor networks (WSNs) that are used to monitor them have a linear topology. This type of WSN is called a linear sensor network (LSN). In this paper, two distributed algorithms for topology discovery in thick LSNs are presented: the linear backbone discovery algorithm (LBD) and the linear backbone discovery algorithm with x backbone paths (LBDx). Both of them try to construct a linear backbone for efficient routing in LSNs. However, the LBD algorithm has the objective of minimizing the number of messages used during the backbone discovery process. On the other hand, the LBDx algorithm focuses on reducing the number of hops of the data messages transmitted from the nodes to the sink. LBD and LBDx exhibit good properties and efficient performance, which are confirmed by extensive simulations.

Geotechnical slope stability and rockfall debris related safety assessments of rock cuts adjacent to a rail track using aerial photogrammetry data analysis

Transportation infrastructure facilitates the accessibility and mobility of goods, people, and services through its vast network spanning across the USA. The departments of transportation (DOT) agencies face many challenges in monitoring and maintaining these infrastructure assets for continuing their service and operations, especially those located adjacent to slopes in rural and remote areas. Mobilizing and conducting traditional infrastructure inspections in those conditions can be laborious and time-consuming. Also, the unstable or highly weathered rock slopes pose significant rockfall hazards due to the moisture content, intrusion, and temperature changes, transpired over a period of time, causing weathering and rockfalls, ultimately resulting in debris accumulation. Recently, unmanned aerial vehicles (UAVs) in conjunction with close-range photogrammetry techniques are being researched and used ubiquitously for infrastructure monitoring applications in and around mountainous regions. In this study, a rock-cut located in a remote terrain where a rail track was passing through was aerially inspected and imaged for performing a comprehensive safety assessment and analysis to evaluate the stability of rock-cut and ways to assess rockfall safety zones and boundaries. A unique approach was developed by leveraging the aerial mapping and data compilation along with an immersive three-dimensional visualization of slopes for conducting stability analysis followed by the evaluation of rockfall debris zones adjacent to rail tracks. Successful assessments conducted in this study indicate that the methodologies will benefit the transportation agencies in effectively monitoring and managing transportation infrastructure adjacent to hilly terrains and ensure the maintenance of safe clearance zones needed to safeguard the public and property.

A Gans-Based Deep Learning Framework for Automatic Subsurface Object Recognition From Ground Penetrating Radar Data

Ground penetrating radar (GPR) is a well-known useful tool for subsurface exploration. GPR data can be recorded at a relatively high speed in a continuous way with hyperbolas being artifacts and evidence of disturbances in the soil. Automatic and accurate detection and interpretation of hyperbolas in GPR remains an open challenge. Recently deep learning techniques have achieved remarkable success in image recognition tasks and this has potential for interpretation of GPR data. However, training reliable deep learning models requires massive labeled data, which is challenging. To address the challenges, this work proposes a Generative Adversarial Nets (GANs)-based deep learning framework, which generates new training data to address the scarcity of GPR data, automatically learns features and detects subsurface objects (via hyperbola) through an end-to-end solution. We have evaluated our proposed approach using real GPR B-scan images from rail infrastructure monitoring applications and compared this with the state-of-the-art methods for object detection (i.e. Faster-RCNN, Cascade R-CNN, SSD and YOLO V2). The proposed approach outperforms the existing methods with high accuracy of 97% being the mean Average Precision (mAP). Moreover, the proposed approach also demonstrates the good generalizability through cross-validation on independent datasets.

A low-acceleration measurement using anti-vibration table with low-frequency resonance

This manuscript describes how NMIJ isolates interferometer optics from the ground vibration for low-acceleration measurement by installing an anti-vibration table. Such a vibration isolation system is designed for an accelerometer calibration system to reduce vibration noise from the microtremor or from reaction of the vibration exciter. Mitigating the vibration of optics enables evaluation of accelerometers at small amplitudes, which is required in aerospace or infrastructure monitoring applications. In this manuscript, vibration transmissibility of the anti-vibration table is measured using a triaxial seismometer, and its benefit in the calibration system is discussed.

Modeling and Performance Evaluation of the IEEE 802.15.4K CSMA/CA with Priority Channel Access Mechanism Under Fading Channel

The IEEE 802.15.4 is a well-known standard that is widely utilized for Wireless Sensor Networks due to its low rate and energy efficiency. A novel amendment IEEE 802.15.4k is released for the support of the requirements of critical infrastructure monitoring applications. It is intended to deal with priority packet using the Priority Channel Access (PCA). In this paper, we introduce a new IEEE 802.15.4k protocol through embedding Markov chain models, namely a two dimensional Markov chain model for the IEEE 802.15.4k slotted CSMA/CA with PCA backoff access channel mechanism for priority packet transmission and a three dimensional Markov chain model for the IEEE 802.15.4k CSMA/CA access channel mechanism for non priority packet transmission. Our new model takes into account retry limits, acknowledgment mechanisms, transmission errors and saturated traffic. Furthermore, to test and validate the developed protocol a detailed mathematical expressions of the reliability, power consumption, average delay for successful packet transmission and throughput are given in order to compare the performance of both mechanisms. Moreover parameters that significantly influence on the performance of the network such as network size, Bit Error Rate, packet length and probability that the available packet is priority are analyzed to determine their impact. The obtained numerical results show that a higher reliability, lower throughput, negligible power consumption and lower delay are observed in our new protocol due to the priority channel access instead of the ordinary channel access. Additionally, we conduct a comparative study between our new IEEE 802.15.4k CSMA/CA mechanism and the IEEE 802.15.4 CSMA/CA mechanism. To the best of our knowledge, this is the first work modeling the 802.15.4k mechanisms and evaluating theirs performance under fading channel.

Linear Wireless Sensor Networks Energy Minimization Using Optimal Placement Strategies of Nodes

Nowadays, the recent developments in the field of wireless sensor networks (WSNs) have initiated new applications of WSNs which can be used in many fields, such as military, environment, health, home and industry. One of the emerged wireless sensor networks topologies are linear wireless sensor networks (LWSNs). They have been rising as a great focus area of research. Such wireless sensor networks have a large number of applications such as border monitoring, railway track monitoring, structural health monitoring of bridges, health care and machines surveillance. LWSNs are widely applied in oil and gas pipelines infrastructure monitoring applications to enable the automatic measurement, analyses, storage and transmission of real-time data. Minimization of energy consumption of LWSNs is crucial for their proper usage. Using two different system models, this research investigates the minimization of LWSNs energy consumption using optimal node placement strategies compared to simple equal-distance placement scheme.

3-D Imaging of Materials at 0.1 THz for Inner- Defect Detection Using a Frequency-Modulated Continuous-Wave Radar

This article reports a novel 3-D imaging approach for remote, nondestructive material inspection at depth. The approach is based on a frequency-modulated continuous-wave (FMCW) radar system operating in the 75-110-GHz frequency band. Time-domain spectroscopy (TDS) measurements demonstrate that such a frequency band has manage-able attenuation levels in centimeter-long materials, thereby offering an advantageous resolution-versus-measurement-depth tradeoff compared with higher frequencies. The proposed setup includes a long delay on the reference signal in order to cancel redundant signals that would otherwise degrade the measurement. Furthermore, specific signal-processing techniques used to improve the performance of the system, which requires stringent component performances in terms of radio-frequency nonlinearity and return loss, are presented. Radio-frequency nonlinearity correction is based on a reference measurement, and the impact of deleterious reflections is reduced by averaging measurements conducted on a target at different longitudinal positions. As a result, an improvement of the signal-to-noise (S/N) ratio up to 20 dB is demonstrated. Tomography experiments were conducted on building materials showing 3-D imaging with theoretically limited longitudinal and transverse resolutions of 5 and 20 mm, respectively, thus opening the door to civil infrastructure monitoring applications.

Energy Harvesting is Charging Up

There have been a number of energy harvesting systems proposed over the years and they have seen varying degrees of adoption. The motivation for energy harvesting varies according to the class of application: 1) In green energy applications, solar harvesting has seen widespread adoption to offset rising energy costs and to reduce CO2 emissions, 2) In infrastructure monitoring applications, low power sensors have made use of solar and thermal harvesting to avoid restrictive battery maintenance when deploying sensors at scale, and 3) in mobile applications, harvesting has been used to extend device battery lifetime and the charging burden imposed on the end user. In short, mobile computing systems focus on energy harvesting as a technique to relax or eliminate dependencies on batteries.

Design and Evaluation of IoT-Enabled Instrumentation for a Soil-Bentonite Slurry Trench Cutoff Wall

In this work, we describe our approach and experiences bringing an instrumented soil-bentonite slurry trench cutoff wall into a modern IoT data collection and visualization pipeline. Soil-bentonite slurry trench cutoff walls have long been used to control ground water flow and contaminant transport. A Raspberry Pi computer on site periodically downloads the sensor data over a serial interface from an industrial datalogger and transmits the data wirelessly to a gateway computer located 1.3 km away using a reliable transmission protocol. The resulting time-series data is stored in a MongoDB database and data is visualized in real-time by a custom web application. The system has been in operation for over two years achieving 99.42% reliability and no data loss from the collection, transport, or storage of data. This project demonstrates the successful bridging of legacy scientific instrumentation with modern IoT technologies and approaches to gain timely web-based data visualization facilitating rapid data analysis without negatively impacting data integrity or reliability. The instrumentation system has proven extremely useful in understanding the changes in the stress state over time and could be deployed elsewhere as a means of on-demand slurry trench cutoff wall structural health monitoring for real-time stress detection linked to hydraulic conductivity or adapted for other infrastructure monitoring applications.

A Fiber-Optic Displacement Sensor Using the Spectral Demodulation Method

This paper reports a fiber-optic displacement sensor based on a Michelson interferometer using the spectral demodulation method. The displacement information is sensed through the length variation of the sensing fiber following the deformation of the measured object. By deploying the relaxed reference arm along the sensing arm, the optical path difference variation introduced by temperature can be eliminated. A spectral demodulation method is employed to obtain the displacement from the interference spectrum by using the fast Fourier transform and the Buneman frequency estimation. The experimental results show that the proposed displacement sensor has a high resolution of 90 nm over a long span of 15.7 m and a large displacement measurement range of 7.5 mm. The theoretical displacement measurement range of the proposed sensor can be up to 10 cm. The proposed displacement sensor will be very useful and promising in large-scale civil infrastructure monitoring applications.

Micro-Doppler Reconstruction in Spaceborne SAR Images Using Azimuth Time–Frequency Tracking of the Phase History

This letter proposes a micro-Doppler (m-D) reconstruction method for spaceborne synthetic aperture radar (SAR) images using azimuth time–frequency tracking of the phase history. The algorithm involves an azimuth defocusing of the SAR image in order to gain access to the phase history, followed by a time–frequency tracking algorithm. The tracking in azimuth is based on local polynomial phase modeling using as estimator for the polynomial coefficients the high-order ambiguity function. The approach is presented in the context of vibration estimation for infrastructure monitoring applications, with an emphasis on the estimation of vibration parameters from the reconstructed m-D. The procedure is tested and compared with state-of-the-art methods by various simulation scenarios in keeping with typical high-resolution SAR imaging parameters. Finally, the developed algorithm is applied on real data acquired by the TerraSAR-X satellite over the Puylaurent water dam in France.

Content centric routing in IoT networks and its integration in RPL

Internet of Things (IoT) networks can be used for many applications across different industry domains including infrastructure monitoring, civil service, security and surveillance applications etc. However, gathering large amounts of data from such networks including images and videos often cause traffic congestion in the central network area. In order to solve this problem, we proposed the content centric routing (CCR) technology, where routing paths are determined by content. By routing the correlated data to intermediate relay nodes for processing, a higher data aggregation ratio can be obtained, hence effectively reducing the traffic in the network. As a result, significant latency reduction can be achieved. Moreover, redundant data transmissions can also be eliminated after data aggregation which reduces the energy consumption spent predominantly on wireless communication thereby conserving limited battery. CCR was further integrated with the IETF RPL protocol and implemented in Contiki OS using the TelosB platform. Finally, both simulation and implementation results prove the superior performance of CCR in terms of low network latency, high energy efficiency, and high reliability.

Combining spaceborne SAR images with 3D point clouds for infrastructure monitoring applications

The measurement and monitoring of critical infrastructure elements by remote sensing has become necessary for economical and security reasons. Information provided by remote sensing for infrastructure monitoring is extracted with specific signal processing chains that have to be adapted to the geometric particularities of the structure. In this paper we present in detail the first monitoring results obtained by combining spaceborne synthetic aperture radar (SAR) data with externally measured point clouds describing an infrastructure element. The processing core is essentially based on refocusing each available SAR image on the provided point cloud and identifying the scatterers that can be monitored by means of four dimensional tomography. The key points and limitations which appear in the measurement and data processing are illustrated on two test sites in France: the Puylaurent water-dam and the Chastel landslide. The SAR products used are high-resolution sliding spotlight SAR images acquired in the TerraSAR-X and TanDEM-X missions, whereas the point clouds of the structures were generated using GPS localization, topographic measurements and laser scans. The estimated deformations of the scatterers using the SAR images were in good agreement with available in-situ data provided through regular topographic surveys and embedded measuring systems.

Scattering Centers Detection and Tracking in Refocused Spaceborne SAR Images for Infrastructure Monitoring

Infrastructure monitoring applications can require the tracking of slowly moving points of a certain structure. Given a certain point from a structure to be monitored, in the context of available spaceborne synthetic aperture radar (SAR) products, where the image is already focused in a slant range—azimuth grid, it is not obvious if this point is the scattering center, if it is in layover or if it is visible from the respective orbit. This paper proposes a scattering centers detection and tracking procedure based on refocusing a set of SAR images on a provided high-resolution grid of the structure. The refocusing procedure is designed for high-resolution spotlight and sliding spotlight SAR images and consists of an azimuth defocusing followed by a modified back-projection algorithm on the given set of points. The scattering centers of the refocused image are detected in the 4-D tomography framework by testing if the main response is at zero elevation in the local elevation–velocity spectral distribution obtained using the Capon estimator. The mean displacement velocity is estimated from the peak response on the zero elevation axis, whereas the displacements time series for detected single scatterers is obtained as phase difference of complex amplitudes. The algorithm is tested by simulations with an emphasis on its behavior for a low number of satellite passes and applied on real data acquired with the TerraSAR-X satellite over the Puylaurent dam. The relative displacements between scattering regions show very good agreement with in situ measurements.

Energy Efficient MAC Protocol for Low-Energy Critical Infrastructure Monitoring Networks Using Wakeup Radio

Critical infrastructure monitoring applications are rapidly increasing. Application requirements include reliable data transfer, energy efficiency, and long deployment lifetime. These applications must also be able to operate in an extremely low-cost communication environment in order to be attractive to potential users. A low rate wireless personal area network can help control and manage the operations of such applications. In this paper, we present a medium access control (MAC) protocol for low-energy critical infrastructure monitoring (LECIM) applications. The proposed MAC protocol is based on a framed slotted aloha multiple access schemes. For downlink communication, we use a wakeup radio approach to avoid complex bookkeeping associated with the traditional MAC protocols. Analytical expressions for power consumption and delay are derived to analyze and compare the performance of our proposed protocol with the existing well-known T-MAC, B-MAC, X-MAC, ZigBee, and WiseMAC protocols. It is shown that our proposed protocol outperforms all the other protocols in terms of power consumption and delay.