Sparse Sensor Networks Research Articles

Accelerated strategies for impact identification of composite laminate using sparse sensor networks and model-based virtual time reversal

Barely visible impact damages are notorious threats to the health of composite structures. Detection of the impact is critical to promise the performance of composite structures. Recently, the authors proposed an impact identification method based on sparse sensor networks and virtual time reversal, which is verified on composite laminates. However, the computational demands of virtual time reversal simulations pose a notable limitation to this approach. To improve the efficiency of the method, several acceleration measures are developed in this article. First, the re-emitted wavefield analysis is accelerated using a frequency-domain method rather than the time-domain simulation, which largely reduces the computational costs. Subsequently, the GPU parallel acceleration algorithm is configured to further improve the efficiency. The proposed acceleration strategy is experimentally validated by various impact events on a composite laminate. The results render that the proposed acceleration strategy can promise the accuracy of the results of impact identification while significantly promoting computational efficiency, in which the time consumption plummets to only 1.94 s. Moreover, factors affecting the efficiency of the proposed method are discussed. The time consumption is positively correlated with the number of sensors involved in the identification. In addition, as the number of candidate points increases, the GPU encounters difficulty in handling all complex matrix operations simultaneously, leading to a substantial rise in computation time. Furthermore, the effect of signal lengths on the efficiency is minimal and largely negligible.

Indeterministic Data Collection in UAV-Assisted Wide and Sparse Wireless Sensor Network

The widespread adoption of Internet of Things (IoT) applications has driven the demand for obtaining sensor data. Using unmanned aerial vehicles (UAVs) to collect sensor data is an effective means in scenarios with no ground communication facilities. In this paper, we innovatively consider an indeterministic data collection task in a UAV-assisted wide and sparse wireless sensor network, where the wireless sensor nodes (SNs) obtain effective data randomly, and the UAV has no pre-knowledge about which sensor has effective data. The UAV trajectories, SN serve scheduling and UAV-SN association are jointly optimized to maximize the amount of collected effective sensing data. We model the optimization problem and address the indeterministic effective indicator by introducing an effectiveness probability prediction model. The reformulated problem remains challenging to solve due to the number of constraints varying with the variable, i.e., the serve scheduling strategy. To tackle this issue, we propose a two-layer modified knapsack algorithm, within which a feasibility problem is resolved iteratively to find the optimal packing strategy. Numerical results demonstrate that the proposed scheme has remarkable advantages in the sum of effective data blocks, reducing the completion time for collecting the same ratio of effective data by nearly 30%.

Deep Learning-Based Transmitter Localization in Sparse Wireless Sensor Networks.

In the field of wireless communication, transmitter localization technology is crucial for achieving accurate source tracking. However, the extant methodologies for localization face numerous challenges in wireless sensor networks (WSNs), particularly due to the constraints posed by the sparse distribution of sensors across large areas. We present DSLoc, a deep learning-based approach for transmitter localization in sparse WSNs. Our method is based on an improved high-resolution network model in neural networks. To address localization in sparse wireless sensor networks, we design efficient feature enhancement modules, and propose to locate transmitter locations in the heatmap using an image centroid-based method. Experiments conducted on WSNs with a 0.01% deployment density demonstrate that, compared to existing deep learning models, our method significantly reduces the transmitter miss rate and improves the localization accuracy by more than double. The results indicate that the proposed method offers more accurate and robust performance in sparse WSN environments.

Large-area inspection of defects in metal plates using multi-mode guided acoustic waves and sparse sensor networks

Various types of defects can be induced during the manufacturing or operation of engineering structures. For effective detection and characterization of the defects in large engineering structures, this paper proposes a large-area inspection technique that combines multi-mode guided acoustic waves with sparse sensor networks. The basic sparse sensor network employed in this study is composed of one transmitter and three receivers, distributed in a square lattice on the test plates. Multi-mode guided waves were excited and acquired by means of commercial single-element sensors of the network. To experimentally demonstrate the proposed technique, four different types of defects were simulated in aluminum test plates, including aluminum tape-based material addition, drilled material loss, indented deformation, and thermal embrittlement. For the evaluation of defects, acoustic response of each defect was analyzed based on the combination of linear vs. nonlinear acoustic characteristics, dependence on the type of the guided acoustic mode, and the directionality of the acoustic response on the network. Results indicate that each of the four representative defects can be uniquely identified (classified) and quantified using the proposed technique.

Intelligence Sparse Sensor Network for Automatic Early Evaluation of General Movements in Infants.

General movements (GMs) have been widely used for the early clinical evaluation of infant brain development, allowing immediate evaluation of potential development disorders and timely rehabilitation. The infants' general movements can be captured digitally, but the lack of quantitative assessment and well-trained clinical pediatricians presents an obstacle for many years to achieve wider deployment, especially in low-resource settings. There is a high potential to explore wearable sensors for movement analysis due to outstanding privacy, low cost, and easy-to-use features. This work presents a sparse sensor network with soft wireless IMU devices (SWDs) for automatic early evaluation of general movements in infants. The sparse network consisting of only five sensor nodes (SWDs) with robust mechanical properties and excellent biocompatibility continuously and stably captures full-body motion data. The proof-of-the-concept clinical testing with 23 infants showcases outstanding performance in recognizing neonatal activities, confirming the reliability of the system. Taken together with a tiny machine learning algorithm, the system can automatically identify risky infants based on the GMs, with an accuracy of up to 100% (99.9%). The wearable sparse sensor network with an artificial intelligence-based algorithm facilitates intelligent evaluation of infant brain development and early diagnosis of development disorders.

Excess Emission Sources Identification via Sparse Monitoring Networks

Abnormality detection and identification is of great concern for complex processes monitoring. In chemical industrial parks (CIPs), the primary task is to identify abnormal (excess) sources when unexpected excess emissions occur. However, it is an ill-posed problem to detect, especially to identify them in dense industrial areas where a vast number of emission sources are concentrated in limited space, challenging the relatively sparse wireless sensor networks (WSNs). Meanwhile, barely detecting the existence rather than identifying excess sources can hardly meet the requirements of fine management in CIPs. In this paper, a QR decomposition-based method for excess sources identification (QR-ESI) has been proposed. By introducing equivalent sources (ES) as a substitute for real sources (RS), the semi-independent relation between ES and RS has been developed. By monitoring ES, excess sources can be inferred progressively through the iteration of logical judgments. The performance was evaluated with simulated data and then validated and compared with a state-of-the-art method in a case study in a real-world chemical industrial park.

On transmission range of sensors in sparse wireless sensor networks

One of the main challenges in the design of wireless ad-hoc and sensor networks is to reduce energy consumption and radio interference and collision, which are strictly and strongly correlated to the transmission range of the nodes. In this article, the transmission ranges of sensors in sparse Wireless Sensor Networks (WSN) is theoretically analyzed and is shown that the transmission ranges of sensors can be significantly reduced in this type of WSNs without losing any connection. Next, a method is presented to calculate reduced transmission ranges. In this method, an iterative transmission range adjustment mechanism is used to select an almost transmission range while no information is needed on the location of nodes or the distance between nodes. This method is very efficient and its communication overhead is low. It can be used as a pre-step of any routing algorithm in order to decrease energy consumption and radio interference in targeted scenarios. The simulation results show the efficiency of the proposed method. We got at least 50% improvement in energy consumption in comparison with full power network, in sparse WSNs.

Time series analysis and sparse sensor network-based impact monitoring for aircraft complex structures

An impact monitoring method based on time series analysis and a sparse sensor network is proposed to identify the location of the impact event that occurs on aircraft complex structures and estimate the impact energy. Generally, a high-density sensor network is required for high localization accuracy of the impact event, but with the trade-off of high deployment costs. A sparse piezoelectric sensor network together with a coarse and fine two-step localization method is designed to balance accuracy and cost. The stress wave signals caused by impact are measured by the sensor network and regarded as time series. The impact localization problem is converted into a classification problem of time series, and the strategy of combining coarse localization (impact zone identification) and fine localization (impact localization within a zone) is used to achieve accurate identification of the impact locations. The zone where the impact event is located is first identified by the coarse localization algorithm based on K-nearest neighbor and dynamic time warping (DTW) and one-dimensional convolutional neural networks, respectively. Furthermore, the high accuracy identification of the impact location within the zone is achieved by the fine localization algorithm based on DTW and centroid localization. In terms of the impact energy estimation, the zone correction compensation algorithm is given to sufficiently reduce the estimation error of the impact energy. The low-velocity impact tests are performed on the composite stiffened panel and the aluminum alloy aircraft fuselage structure to verify the effectiveness of the proposed methods.

Towards real-time prediction of velocity field around a building using generative adversarial networks based on the surface pressure from sparse sensor networks

In this study, we used machine learning techniques to predict instantaneous velocity fields around a single building, where a limited amount of surface pressure data obtained from sparse sensor networks were used as the model input. We found that the model based on mean square error (MSE) can reproduce large flow structures appropriately by mapping their relationships to the surface pressure data. However, this model tends to average the effects of small structures, resulting in their absence in the predicted field and significant underestimations of the turbulent kinetic energy and Reynolds stresses. On the other hand, the velocity fields generated by generative adversarial networks (GANs) provide authentic flow structures and can provide relatively accurate statistics. However, this model is unconstrained in generating large flow structures, resulting in unnecessary errors. The blending of GAN and MSE losses with an appropriate blending factor provides a balance, wherein the predictable large flow structures were learnt by minimizing MSE, and the unpredictable small flow structures were generated by GAN with reasonable statistics. Finally, the model needs sufficient surface pressure monitors to predict flow structures, but the prediction results are not sensitive to the number of monitoring points when it exceeds the critical number.

Environmental impact assessment of guided wave-based structural health monitoring

Guided wave-based structural health monitoring (GW-SHM) relies on permanently installed sensors to detect and monitor structural defects such as cracks or delamination. Millimeter to centimeter-sized defects are detected over areas of several square meters with sparse sensor networks installed on metallic or composite structures. So far, the main drivers of the development of such technologies have been expectations of cost savings and/or an increased safety. As monitoring requires a complex cyber physical system including, at least an energy source, sensors, data acquisition, treatment, and communication capabilities, adding monitoring capabilities to a structure leads to an intrinsic environmental impact. This paper targets for the first time the environmental assessment of GW-SHM. Such analysis being use-case dependent, two prospective applications are studied: railroad monitoring and wind turbine monitoring. A complete GW-SHM system prototype is defined to quantify its environmental impact, and exploitation scenarios are proposed to estimate the potential environmental gains provided by the monitoring. For the scenarios under consideration, the studied system is found to be either carbon neutral or carbon negative (i.e., favorable), but this result is limited to the functional units under consideration. The present study is expected to be a template for further environmental assessments of monitoring systems, which shall be conducted for each prospective application and refined often as systems mature and exploitation scenarios become clearer and exploitation data available.

An Approach to Environmental Monitoring in Sparse Linear Wireless Sensor Networks for Energy Conservation Using Dual Sinks

An Approach to Environmental Monitoring in Sparse Linear Wireless Sensor Networks for Energy Conservation Using Dual Sinks

Imaging damage in plate waveguides using frequency-domain multiple signal classification (F-MUSIC)

Earlier, an ameliorated MUSIC (Am-MUSIC) algorithm is developed by the authors [1], aimed at expanding conventional MUSIC algorithm from linear array-facilitated nondestructive evaluation to in situ health monitoring with a sparse sensor network. Yet, Am-MUSIC leaves a twofold issue to be improved: i) the signal representation equation is constructed at each pixel across the inspection region, incurring high computational cost; and ii) the algorithm is applicable to monochromatic excitation only, ignoring signal features scattered out of the excitation frequency band which also carry information on structural integrity. With this motivation, a multiple-damage-scattered wavefield model is developed, with which the signal representation equation is constructed in the frequency domain, avoiding computationally expensive pixel-based calculation – referred to as frequency-domain MUSIC (F-MUSIC). F-MUSIC quantifies the orthogonal attributes between the signal subspace and noise subspace inherent in signal representation equation, and generates a full spatial spectrum of the inspected sample to visualize damage. Modeling in the frequency domain endows F-MUSIC with the capacity to fuse rich information scattered in a broad band and therefore enhance imaging precision. Both simulation and experiment are performed to validate F-MUSIC when used for imaging single and multiple sites of damage in an isotropic plate waveguide with a sparse sensor network. Results accentuate that effectiveness of F-MUSIC is not limited by the quantity of damage, and imaging precision is not downgraded due to the use of a highly sparse sensor network – a challenging task for conventional MUSIC algorithm to fulfil.

Ameliorated-multiple signal classification (Am-MUSIC) for damage imaging using a sparse sensor network

Multiple Signal Classification (MUSIC) – a directional scanning and searching algorithm, has gained its prominence in phased array-facilitated nondestructive evaluation. Nevertheless, prevailing MUSIC algorithms are largely bound up with the use of a dense linear array, which fail to access the full planar area of an inspected sample, leaving blind zones to which an array fails to scan, along with the incapability of differentiating multiple damage sites that are close one from another. To break above limitations, conventional MUSIC algorithm is ameliorated in this study, by manipulating the signal representation matrix at each pixel using the excitation signal series, instead of the scattered signal series, which enables the use of a sparse sensor network with arbitrarily positioned transducers. In the ameliorated MUSIC (Am-MUSIC), the orthogonal attributes between the signal subspace and noise subspace inherent in the signal representation matrix is quantified, in terms of which the Am-MUSIC yields a full spatial spectrum of the inspected sample, and damage, if any, can be visualized in the spectrum. Am-MUSIC is validated, in both simulation and experiment, by evaluating single and multiple sites of damage in plate-like waveguides with a sparse sensor network. Results verify that i) detectability of Am-MUSIC-driven damage imaging is not limited by damage quantity; ii) Am-MUSIC has full access to a sample, eliminating blind zones; and iii) the amelioration expands conventional MUSIC from phased array-facilitated nondestructive evaluation to health monitoring using built-in sparse sensor networks.

Automatic identification of dense damage-sensitive features in civil infrastructure using sparse sensor networks

Widespread monitoring of bridges is yet rarely employed at a territorial level due to the high costs of monitoring systems. However, the aging of civil infrastructures, combined with the growing traffic demand, poses the need for a simple and automatic tool that helps emergency management. In this paper, an integrated algorithm for the identification of dynamic and dense quasi-static structural features exploiting moving vehicles is proposed. Filtering raw acceleration structural responses, triggered by passing vehicles, enables the identification of modal parameters and curvature influence lines. The procedure can be implemented efficiently as its main computational core consists of convolutions. The definition of a curvature-based damage index leads to accurate localization and quantification of structural anomalies using few sensors. The proposed procedure is tested on three viaducts of the Italian A24 motorway. Moreover, a numerical model is studied to evaluate the potentialities of the strategy for damage localization.

Evaluation of Node-Metastasis in Sparse Underwater Acoustic Sensor Networks for Localization Under Acoustically Stratified Malicious Node Conditions

Malicious anchor node is a serious issue in underwater sensor networks. This problem gets compounded under sparse deployment scenario. To overcome this issue, the authors present a compressed sensing theorem (abbreviated as CS-MC Theorem) which would be applicable to underwater localization. To counter malicious node behavior, CS-MC Theorem is justified through three lemmas. For underwater acoustic propagation, a specific L1-norm minimization method is derived. It describes the condition for unique localization of target by discretizing the target search space. Malicious node is identified by inserting the anchor nodes into the discretized grid. An insertion vector concept is introduced to determine the extent of node metastasis. Derivations are performed to prove the mathematical basis of the proposed algorithm under acoustically stratified and unstratified scenarios. Numerical results establish the feasibility of CS-MC algorithm for sparse underwater acoustic sensor network.

Beyond RSS: A PRR and SNR Aided Localization System for Transceiver-free Target in Sparse Wireless Networks

Nowadays transceiver-free (also referred to as device-free) localization using Received Signal Strength (RSS) is a hot topic for researchers due to its widespread applicability. However, RSS is easily affected by the indoor environment, resulting in a dense deployment of reference nodes. Some hybrid systems have already been proposed to help RSS localization, but most of them require additional hardware support. In order to solve this problem, in this paper, we propose two algorithms, which leverage the Packet Received Rate (PRR) to help RSS localization without additional hardware support. Moreover, we take the environment noise information into consideration by utilizing the Signal-to-Noise Ratio (SNR) which is based on the RSS and Noise Floor (NF) information instead of pure RSS. Thus, we can alleviate the noise effect in the environment and make our system more sensitive to the target. Specifically, when reference nodes are sparsely deployed and RSS is very weak, PRR and SNR can help in performing localization more accurately. Our BEYOND RSS system is based on sparse wireless sensor networks, wherein the experimental results show that the average localization error of our approach outperforms the pure RSS based approach by about 15.19%.

Fast Consensus-Based Time Synchronization Protocol Using Virtual Topology for Wireless Sensor Networks

Slow convergence is a major drawback of average-based consensus time synchronization protocols, particularly in large or sparse wireless sensor networks. The convergence speed can be increased by adding more nodes or increasing the transmission range of nodes, because the network becomes strongly connected. However, these solutions are not always feasible owing to hardware constraints. In this article, a virtual topology-based time synchronization protocol (VTSP) is proposed to address the aforementioned drawback of consensus-based protocols. Notably, VTSP performs the consensus process on a virtual topology that has a stronger algebraic connectivity than a physical one. Therefore, VTSP can significantly accelerate convergence speed without modifying the physical structure of the network. The virtual topology is formed by creating virtual links between each node and its two-hop neighbors. Moreover, two optimization techniques are suggested for reducing data redundancy, which is caused during the creation of the virtual links, in timing messages and for speeding up the convergence by excluding edge nodes from the consensus process. Simulation results demonstrate that VTSP can achieve convergence three times faster than the gradient time synchronization protocol, a well-known consensus-based time synchronization protocol, in various topologies while preserving the same level of accuracy.

BazNet: A Deep Neural Network for Confident Three-component Backazimuth Prediction

As the Treaty Monitoring Community seeks to lower detection thresholds across its sparse sensor network, single-station location estimates and accurate backazimuth predictions become increasingly important. Accurate backazimuth predictions are traditionally limited to array stations, where beamforming provides high-confidence backazimuth prediction that can be reliably passed on to the associator. Three-component stations, on the other hand, rely on polarization analysis for backazimuth prediction, which suffers from both high error and low confidence. As such, very few three-component backazimuth predictions are passed on to the association algorithm. This study presents BazNet, a deep neural-network that takes in a three-component seismogram and produces both a backazimuth prediction and corresponding certainty measure. For existing stations with ample historical training data, the technique achieves an overall median absolute deviation of around $$14^{\circ }$$ , a modest improvement over the $$15^{\circ }$$ achieved by polarization. More importantly, each estimate is accompanied by a robust certainty measure, allowing the selection of high-confidence predictions to be passed on to the associator. Using the BazNet certainty measure, roughly 60% of all three-component predictions can be selected with a median absolute deviation of just $$6^{\circ }$$ , which is on par with the predictions from a full beamformed seismic array. This represents a sevenfold improvement over the 8% of signals similarly selectable via polarization analysis. BazNet performance is demonstrated against 10 years of waveform data from 561,154 cataloged arrivals across nine stations selected from the global IMS Network: STKA, CPUP, VNDA, LPAZ, AAK, BOSA, ULM, BATI, INK.

Adaptive Parameter Estimation of IIR System-Based WSN Using Multihop Diffusion in Distributed Approach

Distributed estimation of parameters in wireless sensor networks is taken into consideration to reduce the communication overhead of the network which makes the sensor system energy efficient. Most of the distributed approaches in literature, the sensor system is modeled with finite impulse response as it is inherently stable. Whereas in real time applications of WSN like target tracking, fast rerouting requires, infinite impulse response system (IIR) is used to model and that has been chosen in this work. It is assumed that every sensor node is equipped with IIR adaptive system. The diffusion least mean square (DLMS) algorithm is used to estimate the parameters of the IIR system where each node in the network cooperates themselves. In a sparse WSN, the performance of a DLMS algorithm reduces as the degree of the node decreases. In order to increase the estimation accuracy with a smaller number of iterations, the sensor node needs to share their information with more neighbors. This is feasible by communicating each node with multi-hop nodes instead of one-hop only. Therefore the parameters of an IIR system is estimated in distributed sparse sensor network using multihop diffusion LMS algorithm. The simulation results exhibit superior performance of the multihop diffusion LMS over non-cooperative and conventional diffusion algorithms.

Auto-regressive model based input and parameter estimation for nonlinear finite element models

A novel framework to accurately estimate nonlinear structural model parameters and unknown external inputs (i.e., loads) using sparse sensor networks is proposed and validated. The framework assumes a time-varying auto-regressive (TAR) model for unknown loads and develops a strategy to simultaneously estimate those loads and parameters of the nonlinear model using an unscented Kalman filter (UKF). First, it is confirmed that a Kalman filter (KF) allows to estimate TAR parameters for a measured, earthquake, acceleration time-history. The KF-based framework is then coupled to an UKF to jointly identify unmeasured inputs and nonlinear finite element (FE) model parameters. The proposed approach systematically assimilates different structural response quantities to estimate TAR and FE model parameters and, as a result, updates the FE model and unknown external excitation estimates. The framework is validated using simulated experiments on a realistic three-dimensional nonlinear steel frame subjected to unknown seismic ground motion. It is demonstrated that assuming relatively low order TAR model for the unknown input leads to precise reconstruction and unbiased estimation of nonlinear model parameters that are most sensitive to measured system response.