Search Results (32)

This paper presents a new methodology for localizing impact events on plate-like structures using a proposed two-dimensional convolutional neural network (CNN) and received impact signals. A network of four piezoelectric wafer active sensors (PWAS) was installed on the tested plate to acquire impact signals. These signals consisted of reflection waves that provided valuable information about impact events. In this methodology, each of the received signals was divided into several equal segments. Then, a wavelet transform (WT)-based time-frequency analysis was used for processing each segment signal. The generated WT diagrams of these segments’ signals were cropped and resized using MATLAB code to be used as input image datasets to train, validate, and test the proposed CNN model. Two scenarios were adopted from PAWS transducers. First, two sensors were positioned in two corners of the plate, while, in the second scenario, four sensors were used to monitor and collect the signals. Eight datasets were collected and reshaped from these two scenarios. These datasets presented the signals of two, three, four, and five impacts. The model’s performance was evaluated using four metrics: confusion matrix, accuracy, precision, and F1 score. The proposed model demonstrated exceptional performance by accurately localizing all of the impact points of the first scenario and 99% of the second scenario. The main limitation of the proposed model is how to differentiate the data samples that have similar features. From our point of view, the similarity challenge arose from two factors: the segmentation interval and the impact distance. First, applying the segmenting procedure to the PWAS signals led to an increase in the number of data samples. The procedure segmented each PWAS signal to 30 samples with equal intervals, regardless of the features of the signal. Segmenting and transforming different PWAS signals into image-based data points led to data samples that had similar features. Second, some of the impacts had a close distance to the PWAS sensors, which resulted in similar segmented signals. Therefore, the second scenario was more challenging for the proposed model. Full article

Temperature has a significant impact on the operational lifetime of electronic components, as excessive heat can lead to accelerated degradation and ultimately failure. In safety-critical applications, it is important that real-time monitoring is employed to reduce the risk of system failures and maintain the safety, reliability, and integrity of the connected systems. In the case of printed circuit boards (PCBs), it is often not feasible to install enough sensors to adequately cover all of the temperature sensitive components. In this study, we present a novel method for the temperature monitoring of PCBs using ultrasonic guided waves and machine learning techniques. Our approach utilizes a small number of low-cost, unobtrusive piezoelectric wafer active sensors (PWAS) sensors for propagating ultrasonic guided waves across a PCB. Through interaction with board features, the temperature of components can be predicted using multi-output regression algorithms. Our technique has been applied to three different PCBs, each with five hotspot positions, achieving an RMSE of <3.5 °C and $R^2$ > 0.95 in all three cases. Full article

Guided ultrasonic wave (GUW) analysis is a well-investigated method for structural health monitoring (SHM) applications. For plate-like structures, the pitch-catch technique is a popular choice since it offers the possibility to investigate a large area with a small number of sensors. This method requires a large amount of data to be analyzed to detect and localize damage, with the consequence that, besides the presence of damage, environmental influences like temperature and load will also change the GUW signals. In addition, the location, size, and type of the damage will result in different changes in the GUW signals. Data-driven methods require sufficient data and therefore require data augmentation. In order to get closer to this goal, this study aims to demonstrate the conversion of GUW signals measured with an air-coupled measurement system (ACMS) into signals measured with piezoelectric wafer active sensors (PWAS). This would allow the fast measurement of GUW data with ACMS at different positions of a plate-like specimen and translate it to a surface-bonded PWAS signal without the time-consuming process of transducer mounting. In this study, it is assumed that the measurement methods are not independent of each other when they are measured at the same position. To obtain the transform function from ACMS to PWAS, GUW signals were measured both with ACMS and PWAS for different positions of artificial damage. Since both signal classes are physically dependent, it should be possible to determine the transform function with machine learning (ML) methods. As input, the ACMS time-dependent signal or signal features are used, while the PWAS signals serve as labels for the training process. We are evaluating different ML-based transform model architectures with respect to their suitability for signal or signal feature transformation, e.g., ANN, CNN, and LSTM-based networks, with a particular focus on autoencoders. Full article

Delamination represents one of the most significant and dangerous damages in composite plates. Recently, many papers have presented the capability of structural health monitoring (SHM) techniques for the investigation of structural delamination with various shapes and thickness depths. However, few studies have been conducted regarding the utilization of convolutional neural network (CNN) methods for automating the non-destructive testing (NDT) techniques database to identify the delamination size and depth. In this paper, an automated system qualified for distinguishing between pristine and damaged structures and classifying three classes of delamination with various depths is presented. This system includes a proposed CNN model and the Lamb wave technique. In this work, a unidirectional composite plate with three samples of delamination inserted at different depths was prepared for numerical and experimental investigations. In the numerical part, the guided wave propagation and interaction with three samples of delamination were studied to observe how the delamination depth can affect the scattered and trapped waves over the delamination region. This numerical study was validated experimentally using an efficient ultrasonic guided waves technique. This technique involved piezoelectric wafer active sensors (PWASs) and a scanning laser Doppler vibrometer (SLDV). Both numerical and experimental studies demonstrate that the delamination depth has a direct effect on the trapped waves’ energy and distribution. Three different datasets were collected from the numerical and experimental studies, involving the numerical wavefield image dataset, experimental wavefield image dataset, and experimental wavenumber spectrum image dataset. These three datasets were used independently with the proposed CNN model to develop a system that can automatically classify four classes (pristine class and three different delamination classes). The results of all three datasets show the capability of the proposed CNN model for predicting the delamination depth with high accuracy. The proposed CNN model results of the three different datasets were validated using the GoogLeNet CNN. The results of both methods show an excellent agreement. The results proved the capability of the wavefield image and wavenumber spectrum datasets to be used as input data to the CNN for the detection of delamination depth. Full article

This paper addresses the challenging issue of achieving high spatial resolution in temperature monitoring of printed circuit boards (PCBs) without compromising the operation of electronic components. Traditional methods involving numerous dedicated sensors such as thermocouples are often intrusive and can impact electronic functionality. To overcome this, this study explores the application of ultrasonic guided waves, specifically utilising a limited number of cost-effective and unobtrusive Piezoelectric Wafer Active Sensors (PWAS). Employing COMSOL multiphysics, wave propagation is simulated through a simplified PCB while systematically varying the temperature of both components and the board itself. Machine learning algorithms are used to identify hotspots at component positions using a minimal number of sensors. An accuracy of 97.6% is achieved with four sensors, decreasing to 88.1% when utilizing a single sensor in a pulse–echo configuration. The proposed methodology not only provides sufficient spatial resolution to identify hotspots but also offers a non-invasive and efficient solution. Such advancements are important for the future electrification of the aerospace and automotive industries in particular, as they contribute to condition-monitoring technologies that are essential for ensuring the reliability and safety of electronic systems. Full article

This study conducted experimental and numerical investigations on piezoelectric wafer active sensors (PWASs) bonded to an aluminum plate to assess the impact of bonding degradation on Lamb wave generation. Three surface-bonded PWASs were examined, including one intentionally bonded with a reduced adhesive to create a defective bond. Thermal cyclic aging was applied, monitoring through laser Doppler vibrometry (LDV) and static capacitance measurements. The PWAS with the initially defective bond exhibited the poorest performance over aging cycles, emphasizing the significance of the initial bond condition. As debonding progressed, modifications in electromechanical behavior were observed, leading to a reduction in wave amplitude and distortion of the generated wave field, challenging the validity of existing analytical modeling of wave-tuning curves for perfectly bonded PWASs. Both numerical simulations and experimental observations substantiated this finding. In conclusion, this study highlights the imperative of a high-integrity bond for the proper functioning of a guided wave-based structural health monitoring (SHM) system, emphasizing ongoing challenges in assessing SHM performance. Full article

Piezoelectric materials are defined by their ability to display a charge across their surface in response to mechanical strain, making them great for use in sensing applications. Such applications include pressure sensors, medical devices, energy harvesting and structural health monitoring (SHM). SHM describes the process of using a systematic approach to identify damage in engineering infrastructure. A method of SHM that uses piezoelectric wafers connected directly to the structure has become increasingly popular. An investigation of a novel pitch-catch method of determining instrumentation quality of piezoelectric wafer active sensors (PWASs) used in SHM was conducted as well as an investigation into the effects of defects in piezoelectric sensors and sensor bonding on the sensor response. This pitch-catch method was able to verify defect-less instrumentation quality of pristinely bonded PWASs. Additionally, the pitch-catch method was compared with the electromechanical impedance method in determining defects in piezoelectric sensor instrumentation. Using the pitch-catch method, it was found that defective instrumentation resulted in decreasing amplitude of received and transmitted signals as well as changes in the frequency spectrums of the signals, such as the elimination of high frequency peaks in those with defects in the bonding layer and an increased amplitude of around 600 kHz for a broken PWAS. The electromechanical impedance method concluded that bonding layer defects increase the primary frequency peak’s amplitude and cause a downward frequency shift in both the primary and secondary frequency peaks in the impedance spectrum, while a broken sensor has the primary peak amplitude reduced while shifting upward and nearly eliminating the secondary peak. Full article

A novel kind of acoustic metamaterials (AMMs) with unit cells composed of two layers made of dissimilar materials with a crack-like void situated at the interface between bars is considered. Recently, the authors showed numerically that this novel kind of AMMs can provide unidirectional propagation of guided waves. Several AMM specimens (the finite stack of periodic elastic layers with and without voids) have been manufactured using additive manufacturing techniques and regular gluing. The details of the manufacturing process are discussed. In the experiment, the elastic waves have been excited by a rectangular piezoelectric wafer active transducer bonded at the surface of the specimen. Vibrations of the opposite side of the AMM specimen are measured via a piezoelectric sensor. The band gaps are observed in the experiment and values of their width and location correlate with numerically predicted ones. Full article

Water management is a key issue in the design and operation of proton exchange membrane fuel cells (PEMFCs). For an efficient and stable operation, the accumulation of liquid water inside the flow channels has to be prevented. Existing measurement methods for localizing water are limited in terms of the integration and application of measurements in operating PEMFC stacks. In this study, we present a measurement method for the localization of liquid water based on ultrasonic guided waves. Using a sparse sensing array of four piezoelectric wafer active sensors (PWAS), the measurement requires only minor changes in the PEMFC cell design. The measurement method is demonstrated with ex situ measurements for water drop localization on a single bipolar plate. The wave propagation of the guided waves and their interaction with water drops on different positions of the bipolar plate are investigated. The complex geometry of the bipolar plate leads to complex guided wave responses. Thus, physical modeling of the wave propagation and tomographic methods are not suitable for the localization of the water drops. Using machine learning methods, it is demonstrated that the position of a water drop can be obtained from the guided wave responses despite the complex geometry of the bipolar plate. Our results show standard deviations of 4.2 mm and 3.3 mm in the x and y coordinates, respectively. The measurement method shows high potential for in situ measurements in PEMFC stacks as well as for other applications that require deposit localization on geometrically complex waveguides. Full article

The present paper comprehensively investigates the complex interaction between ultrasonic guided waves and local structural discontinuities, such as damages, through highly sensitive features: so-called wave damage interaction coefficients (WDICs). These WDICs are unique for each structural discontinuity and depend solely on their characteristics for a given structure and condition. Thus, they can be particularly useful for advanced assessment of lightweight structures in the context of non-destructive evaluation and structural health monitoring. However, the practical application of WDICs entails significant difficulties due to their sensitivity and complex patterns. Therefore, this study attempts to guide researchers and practitioners in the estimation of WDICs from numerical simulations and physical experiments. Detailed investigations are made for an aluminum host plate modified by artificial structural discontinuities, i.e., surface-bonded steel sheets. The numerical simulations are performed to predict WDICs and study sensitivities using a sophisticated finite element model. The experimental setup uses piezoelectric transducers to excite guided waves in the host plate. A single scanning laser Doppler vibrometer measures the scattered guided waves caused by the surface-bonded steel sheets, and the resulting WDICs with possible influences are investigated. In both cases, the orientation and thickness of the attached steel sheets were varied to create 12 different damage scenarios. In general, the comparison between numerical and experimental WDICs show good agreement. This underpins the applicability of the general methodology for simulating and measuring WDICs over all scenarios. Furthermore, the WDIC scattering patterns reveal a clear dependency of the peaks in the back-scattered reflections for both the numerical and experimental amplitude coefficients on the damage orientation, basically following the law of reflection. However, some discrepancies between both studies were observed. Numerical sensitivity analysis identified the adhesive layer as one reason for such differences. Additionally, misalignment errors in the experimental measurements were also found to affect WDICs. Therefore, an improved baseline subtraction method is proposed, which clearly enhances the experimental WDICs. Finally, an experimental sensitivity study of WDICs for selected sensing radii revealed only a minor influence. All these investigations were made for the amplitude as well as the phase representation of WDICs. Thus, these findings may open the way to future research and development of techniques employing WDICs for advanced applications of non-destructive evaluation and structural health monitoring. Full article

The acoustic emission (AE) technique has become a well-established method of monitoring structural health over recent years. The sensing and analysis of elastic AE waves, which have involved piezoelectric wafer active sensors (PWAS) and time domain and frequency domain analysis, has proven to be effective in yielding fatigue crack-related information. However, not much research has been performed regarding (i) the correlation between the fatigue crack length and AE signal signatures and (ii) artificial intelligence (AI) methodologies to automate the AE waveform analysis. In this paper, this crack length correlation is investigated along with the development of a novel AE signal analysis technique via AI. A finite element model (FEM) study was first performed to understand the effects of fatigue crack length on the resulting AE waveforms and a fatigue experiment was performed to capture experimental AE waveforms. Finally, this database of experimental AE waveforms was used with a convolutional neural network to build a system capable of performing automated classification and prediction of the length of a fatigue crack that excited respective AE signals. AE signals captured during a fatigue crack growth experiment were found to match closely with the FEM simulations. This novel AI system proved to be effective at predicting the crack length of an AE signal at an accuracy of 98.4%. This novel AI-enabled AE signal analysis technique will provide a crucial step forward in the development of a comprehensive structural health monitoring (SHM) system. Full article

In terms of the structural health inspection of storage tanks by ultrasonic guided wave technology, many scholars are currently focusing on the tanks’ floor and walls, while little research has been conducted on storage tank roofs. However, the roof of a storage tank is prone to corrosion because of its complex structure and unique working environment. For this purpose, this paper proposes a reflection/transmission signal amplitude ratio (RTAR) coefficient method for corrosion depth assessment. We studied the relationship between the RTAR coefficient, the corrosion depth, and the guided wave frequency to establish a depth assessment model. More importantly, unlike the traditional reflection coefficient method, the characteristics of guided wave signals, including the propagation and attenuation, are introduced in this model for accurate assessment. To eliminate the interference of residual vibration and improve the detection accuracy of defects, we built a corrosion detection system by using piezoelectric sensors and carried out field tests to verify the performance of the proposed method. We demonstrate that corrosion defects with a minimum depth of 0.2 mm can be quantitatively evaluated. Full article

Piezoelectric sensors can be embedded in carbon fibre-reinforced plastics (CFRP) for continuous measurement of acoustic emissions (AE) without the sensor being exposed or disrupting hydro- or aerodynamics. Insights into the sensitivity of the embedded sensor are essential for accurate identification of AE sources. Embedded sensors are considered to evoke additional modes of degradation into the composite laminate, accompanied by additional AE. Hence, to monitor CFRPs with embedded sensors, identification of this type of AE is of interest. This study (i) assesses experimentally the performance of embedded sensors for AE measurements, and (ii) investigates AE that emanates from embedded sensor-related degradation. CFRP specimens have been manufactured with and without embedded sensors and tested under four-point bending. AE signals have been recorded by the embedded sensor and two reference surface-bonded sensors. Sensitivity of the embedded sensor has been assessed by comparing centroid frequencies of AE measured using two sizes of embedded sensors. For identification of embedded sensor-induced AE, a hierarchical clustering approach has been implemented based on waveform similarity. It has been confirmed that both types of embedded sensors (7 mm and 20 mm diameter) can measure AE during specimen degradation and final failure. The 7 mm sensor showed higher sensitivity in the 350–450 kHz frequency range. The 20 mm sensor and the reference surface-bounded sensors predominately featured high sensitivity in ranges of 200–300 kHz and 150–350 kHz, respectively. The clustering procedure revealed a type of AE that seems unique to the region of the embedded sensor when under combined in-plane tension and out-of-plane shear stress. Full article

Acoustic waves are widely used in structural health monitoring (SHM) for detecting fatigue cracking. The strain energy released when a fatigue crack advances has the effect of exciting acoustic waves, which travel through the structures and are picked up by the sensors. Piezoelectric wafer active sensors (PWAS) can effectively sense acoustic waves due to fatigue-crack growth. Conventional acoustic-wave passive SHM, which relies on counting the number of acoustic events, cannot precisely estimate the crack length. In the present research, a novel method for estimating the crack length was proposed based on the high-frequency resonances excited in the crack by the energy released when a crack advances. In this method, a PWAS sensor was used to sense the acoustic wave signal and predict the length of the crack that generated the acoustic event. First, FEM analysis was undertaken of acoustic waves generated due to a fatigue-crack growth event on an aluminum-2024 plate. The FEM analysis was used to predict the wave propagation pattern and the acoustic signal received by the PWAS mounted at a distance of 25 mm from the crack. The analysis was carried out for crack lengths of 4 and 8 mm. The presence of the crack produced scattering of the waves generated at the crack tip; this phenomenon was observable in the wave propagation pattern and in the acoustic signals recorded at the PWAS. A study of the signal frequency spectrum revealed peaks and valleys in the spectrum that changed in frequency and amplitude as the crack length was changed from 4 to 8 mm. The number of peaks and valleys was observed to increase as the crack length increased. We suggest this peak–valley pattern in the signal frequency spectrum can be used to determine the crack length from the acoustic signal alone. An experimental investigation was performed to record the acoustic signals in crack lengths of 4 and 8 mm, and the results were found to match well with the FEM predictions. Full article

Barely visible impact damage (BVID) due to low velocity impact events in composite aircraft structures are becoming prevalent. BVID can have an adverse effect on the strength and safety of the structure. During aircraft inspections it can be extremely difficult to visually detect BVID. Moreover, it is also a challenge to ascertain if the BVID has in-fact caused internal damage to the structure or not. This paper describes a method to ascertain whether or not internal damage happened during the impact event by analyzing the high-frequency information contained in the recorded acoustic emission signal signature. Multiple 2 mm quasi-isotropic carbon fiber reinforced polymer (CFRP) composite coupons were impacted using the ASTM D7136 standard in a drop weight impact testing machine to determine the mass, height and energy parameters to obtain approximately 1” impact damage size in the coupons iteratively. For subsequent impact tests, four piezoelectric wafer active sensors (PWAS) were bonded at specific locations on each coupon to record the acoustic emission (AE) signals during the impact event using the MISTRAS micro-II digital AE system. Impact tests were conducted on these instrumented 2 mm coupons using previously calculated energies that would create either no damage or 1” impact damage in the coupons. The obtained AE waveforms and their frequency spectrums were analyzed to distinguish between different AE signatures. From the analysis of the recorded AE signals, it was verified if the structure had indeed been damaged due to the impact event or not. Using our proposed structural health monitoring technique, it could be possible to rapidly identify impact events that cause damage to the structure in real-time and distinguish them from impact events that do not cause damage to the structure. An invention disclosure describing our acoustic emission structural health monitoring technique has been filed and is in the process of becoming a provisional patent. Full article