Search for: All records

Abstract Electronic components that undergo shock and vibration are susceptible to failure caused by damage in the base printed circuit board that makes up the substrate of these systems. In certain applications, it may become paramount to know in real-time if the electronic components are damaged to enable a next-generation active system to take immediate responses. Broad examples of such systems include blast mitigation systems or safety systems in car accidents. These systems on classified under the term “high-rate” as they experience high shock levels on short time scales. This work proposes a long short-term memory neural network to enable real-time damage detection and assessment of electronic assemblies subjected to shock. The long short-term memory neural network is able to infer the state of the structure in approximately 4 milliseconds following the impact. The model obtains perfect classification results at 4 milliseconds for the data used in this work. This work is supported by experimentation that indicates damage to electronic packages can be quantified through the in situ monitoring of the impedance of electrical connections. Changes in impedance correlate to alterations in the physical properties of electronic components which indicate the occurrence of damage. On this basis, a comprehensive dataset is created to monitor the impedance changes of a daisy-chained connection through repeated high-energy shocks. Meanwhile, the shock response of the electronic components is captured using an accelerometer, enabling a detailed analysis of the effects of high-rate shock on the components’ performance. A dataset is developed to encompass 30 repeated impacts experiencing 10,000 gn during impact with an average half-sine time of 322 microseconds. The paper outlines the proposed real-time machine learning framework while performance metrics are presented and discussed in detail. 

Abstract This study presents an approach for structural health monitoring (SHM) of remote and hazardous structures using unpiloted aerial vehicles (UAVs). The method focuses on overcoming the challenges associated with traditional sensor deployment techniques, which are often costly and risky due to the decaying nature of the targeted structures. Utilizing a multi-rotor UAV platform, a streaming camera is integrated into a recovery cone to aid in visual alignment during deployment and retrieval providing a safe and cost-effective means of sensor delivery. The paper covers the design of a video-broadcasting deployment system with integrated electropermanent magnets (EPMs), housed in a 3D-printed recovery cone, supplemented by redundancy measures to enhance safety and reliability. This proposed system significantly improves the user’s spatial awareness and aids in precise sensor package alignment, facilitated by multiple camera views providing a dual purpose of conducting visual inspection in addition to aiding in sensor delivery. The experimental analysis presented in this study validates the system’s effectiveness, demonstrating the utility of camera-aided sensor delivery for rapid SHM applications. Navigation challenges due to proximity to metal structures and the difficulties associated with signal strength and reflections are also reported. The contribution of this work is a methodology for aerial sensor deployment and retrieval using a lightweight 3D-printed recovery cone with integrated cameras for navigation and sensor alignment. 

Abstract To enable real-time control of next-generation active structures during shock events, there is a need to identify the start of a shock event within microseconds of its initiation. The delayed classification of a shock event may cause damage to the system that could have been prevented with assumed next-generation active control mechanisms. Addressing the challenge of ultra-low latency shock event classification requires utilizing prior information on normal behaviors (i.e., the system under vibrational loading) to identify abnormalities that can be classified as features of a shock event. The purpose of changepoint shock classification is to automatically recognize when a structure of interest behaves differently than expected in some measurable way. In this work, we analyze two different methods for shock classification using changepoint methodologies. We study the use of adaptive cumulative summation and expectation maximization algorithms in this work. Each method presents advantages and disadvantages for different scenarios. This study aims to derive features (streams of time series data) for the changepoint algorithms and revise the changepoint models to be used in real-time robust shock event detection. In this work, a printed circuit board under continuous vibrations before, during, and after a shock event is used to investigate the proposed methodologies. The printed circuit board is monitored with an accelerometer that is used to monitor both the vibrational and shock state of the system. The vibrational response of the system consists of accelerations up to 20 m/s2, while the shock event consists of loadings up to 2,000 m/s2. This work showed that the CUSUM algorithm is fairly effective at identifying the shock state in data but generates many false positives during normal behavior times, with no false positives post-shock, indicating accurate shock state detection despite early errors. In contrast, the Expectation Maximization (EM) algorithm shows improved performance by correctly predicting no shock in the initial phase and accurately identifying the onset of the shock state. It occasionally misclassifies shocked points as normal due to its change point identification process. Compared to CUSUM, EM has fewer false positives before the shock and similar performance during and after the shock event. Future research efforts will focus on developing online versions of these algorithms, which can identify system states with a minimum number of errors. The limitations of the system and its robustness to noise are discussed. 

Abstract Levees play a critical role in safeguarding communities and assets from flooding, acting as essential defenses against the devastating impacts of inundation. Yet, earthen levees are prone to breaches, especially in the face of swift floodwaters. Distributed low-cost sensor networks offer the potential to generate spatial maps illustrating soil moisture levels. Long-term monitoring of these spatial maps could identify vulnerable zones in the levee while providing an understanding of how climate change affects levee stability. This study presents an investigation into spatial monitoring of soil saturation in levees using a wireless network of UAV-deployable sensing spike packages. The goal of this paper is to demonstrate the use of these sensors for assessing soil conductivity levels in sand-filled embankments. The obtained soil conductivity levels are crucial for determining soil saturation. The developed sensing spikes consist of a spike that penetrates the ground and measures conductivity between two electrically conductive contacts. The sensing spike consists of microprocessors for edge computing, and wireless data communication systems that report data to a way station in real-time. To validate the efficacy of the developed sensors, a flume test is developed as a replica of a levee and monitored under controlled water flow conditions. The analysis of data at different times revealed the progression of moisture throughout the earthen embankment. Initially, the soil is almost dry. As the controlled water flow proceeds, the soil becomes partially saturated, with the final stage showing a dominant presence of saturated soil. The collected data sampled at the measurement points is expanded to a continuous moisture profile using kriging. Gaussian kriging, also known as ordinary kriging, is one of the commonly used variants of the kriging method. In Gaussian kriging, the estimation of values at unsampled locations is based on a linear combination of nearby data points, with weights determined by their spatial relationships. The Gaussian assumption implies that the errors in the estimation process follow a normal distribution. The extended knowledge about saturation levels obtained through kriging can lead to insights for predicting vulnerable areas and preempting potential failures. Overall, this study paves the way for further development of a wireless network of sensing spike packages as a UAV-deployable system for levee health assessment and improved infrastructure management. 

Heavy rains and tropical storms often result in floods, which are expected to increase in frequency and intensity. Flood prediction models and inundation mapping tools provide decision-makers and emergency responders with crucial information to better prepare for these events. However, the performance of models relies on the accuracy and timeliness of data received from in situ gaging stations and remote sensing; each of these data sources has its limitations, especially when it comes to real-time monitoring of floods. This study presents a vision-based framework for measuring water levels and detecting floods using computer vision and deep learning (DL) techniques. The DL models use time-lapse images captured by surveillance cameras during storm events for the semantic segmentation of water extent in images. Three different DL-based approaches, namely PSPNet, TransUNet, and SegFormer, were applied and evaluated for semantic segmentation. The predicted masks are transformed into water level values by intersecting the extracted water edges, with the 2D representation of a point cloud generated by an Apple iPhone 13 Pro lidar sensor. The estimated water levels were compared to reference data collected by an ultrasonic sensor. The results showed that SegFormer outperformed other DL-based approaches by achieving 99.55 % and 99.81 % for intersection over union (IoU) and accuracy, respectively. Moreover, the highest correlations between reference data and the vision-based approach reached above 0.98 for both the coefficient of determination (R2) and Nash–Sutcliffe efficiency. This study demonstrates the potential of using surveillance cameras and artificial intelligence for hydrologic monitoring and their integration with existing surveillance infrastructure. 

Abstract Levees are built to safeguard human lives, essential infrastructure, and farmland. However, failure of levees can have catastrophic impacts due to a fast rate of inundation in areas protected by levees. Earthen levees are prone to failure due to excessive moisture content that reduces the shear strength of the soil. The use of levee monitoring systems has demonstrated the ability to reduce the likelihood of failure by creating maps that depict the saturation levels of the surface of the levee, both in terms of space and time. By utilizing extensive sensor networks to continuously monitor these geo-infrastructure systems, the structural deterioration attributed to changing climate can be studied. Measuring environmental parameters surrounding such structures provides insight into the potential stressors that cause structural failure. Steps can then be taken to mitigate those effects on the levees and maintain structural integrity. However, the massive scale of levees makes it difficult to monitor with conventional wired sensors. This paper presents a preliminary investigation into the development and validation of UAV-deployable smart sensing spikes for soil conductivity levels in levees, which is a measurement modality for determining soil saturation levels. For this work, Gaussian process regression (also known as kriging) is used to model the soil saturation levels between sensing spikes obtaining a continuous moisture map of the levees. The expanded data is then categorized using a clustering-based machine learning approach with conductivity data from sensing spikes as model inputs. The machine learning model output is sorted into three categories: dry, partially saturated, and saturated soil. The findings of a laboratory study are presented, and the implications of the raw and expanded data are discussed. This work will aid in predicting potential levee failure risks and maintenance requirements based on the analysis of the soil conditions using a network of smart sensing spikes.