Structural health monitoring (SHM) plays a pivotal role in ensuring the integrity and safety of critical infrastructure and mechanical components. While traditional non-destructive testing (NDT) methods offer high-resolution data, they typically require periodic access and disassembly of equipment to conduct inspections. In contrast, SHM employs permanently installed, cost-effective sensors to enable continuous monitoring, though often with reduced detail. This study presents an integrated hybrid SHM-NDT methodology enhanced by deep learning to enable the real-time monitoring and classification of mechanical stresses in structural components. As a case study, a 6-foot-long parallel flange I-beam, representing bridge truss elements, was subjected to variable bending loads to simulate operational conditions. The hybrid system utilized an ultrasonic transducer (NDT) for excitation and piezoelectric sensors (SHM) for signal acquisition. Signal data were analyzed using 1D and 2D convolutional neural networks (CNNs), long short-term memory (LSTM) models, and random forest classifiers to detect and classify load magnitudes. The AI-enhanced approach achieved 100% accuracy in 47 out of 48 tests and 94% in the remaining tests. These results demonstrate that the hybrid SHM-NDT framework, combined with machine learning, offers a powerful and adaptable solution for continuous monitoring and precise damage assessment of structural systems, significantly advancing maintenance practices and safety assurance.
13 October 2023 in Digital Manufacturing Technology
Additive manufacturing (AM) was originally developed to manufacture polymer prototypes. Today, it has been used for the manufacturing of many critical machine components. Most of the structural health monitoring (SHM) methods were developed for monitoring the condition of large and thin plates on airplane fuselages. Additively manufactured parts are generally small, thick, and have complex geometries. SHM methods have been improved to sense load, detect defects, and identify loose bolts with the help of a permanently installed sensor. In this study, the adaptability of SHM methods was researched with additively manufactured metal parts with complex geometry. Magnets were used to apply pressure to 9 different locations on the surface of a stainless steel additively manufactured thick plate with deep groves. SHM was used to estimate the magnets’ location. Many SHM (Lamb wave) methods cannot work on smaller parts since their dimensions are shorter or very close to the wavelength of the created oscillations. Surface response to excitation (SuRE) method which has similar characteristics to electromechanical impedance methods was used for data collection. To obtain descriptive features of the time domain data, fast Fourier transformation (FFT), short-time Fourier transformation (STFT), continuous wavelet transformation (CWT), and synchrosqueezing transform (SST) were applied to CWT. 1D and 2D convolutional neural networks (CNN) were used to classify the cases. When CNN was optimized for the analysis of our data, 100% location estimation accuracy was obtained by using 50% of 320 scalograms for training. The scalograms were obtained by enhancing the CWT results with SST. STFT-CNN combination was the second best. It obtained 95% accuracy with the same number of spectrograms and training allocation.
Structural health monitoring (SHM) of additively manufactured (AM) small and complex components is investigated using a sensor-based signal processing and machine-learning framework. Guided-wave responses acquired from piezoelectric transducers are analyzed to evaluate the performance of sweep-sine and pulse excitation signals, as well as the influence of infill patterns, part geometry, and defect type on system reliability. Test specimens, including dogbone structures and a simulated rocket-nozzle component, were fabricated using AM, and nonstationary guided-wave signals were recorded and processed. Time–frequency signal representations (scalograms) were generated using the Continuous Wavelet Transform (CWT). Convolutional Neural Networks (CNNs) and Gaussian Mixture Models (GMMs) were employed for supervised classification and unsupervised clustering, respectively. Sweep-sine excitation consistently yielded higher classification accuracy, with CNN analysis achieving near-perfect performance and GMM clustering demonstrating improved group separability. In contrast, pulse excitation revealed transient signal features associated with wave interactions, including reflections, mode conversion, and scattering, highlighting its potential for complementary signal-based diagnostics. Importantly, the proposed hybrid supervised–unsupervised learning framework enables the quantification of previously unseen intermediate load states, demonstrating strong adaptability and generalizability beyond the conditions represented in the training data.