VpROM: a novel variational autoencoder-boosted reduced order model for the treatment of parametric dependencies in nonlinear systems.

Reduced Order Models (ROMs) are of considerable importance in many areas of engineering in which computational time presents difficulties. Established approaches employ projection-based reduction, such as Proper Orthogonal Decomposition. The limitation of the linear nature of such operators is typically tackled via a library of local reduction subspaces, which requires the assembly of numerous local ROMs to address parametric dependencies. Our work attempts to define a more generalisable mapping between parametric inputs and reduced bases for the purpose of generative modeling. We propose the use of Variational Autoencoders (VAEs) in place of the typically utilised clustering or interpolation operations, for inferring the fundamental vectors, termed as modes, which approximate the manifold of the model response for any and each parametric input state. The derived ROM still relies on projection bases, built on the basis of full-order model simulations, thus retaining the imprinted physical connotation. However, it additionally exploits a matrix of coefficients that relates each local sample response and dynamics to the global phenomena across the parametric input domain. The VAE scheme is utilised for approximating these coefficients for any input state. This coupling leads to a high-precision low-order representation, which is particularly suited for problems where model dependencies or excitation traits cause the dynamic behavior to span multiple response regimes. Moreover, the probabilistic treatment of the VAE representation allows for uncertainty quantification on the reduction bases, which may then be propagated to the ROM response. The performance of the proposed approach is validated on an open-source simulation benchmark featuring hysteresis and multi-parametric dependencies, and on a large-scale wind turbine tower characterised by nonlinear material behavior and model uncertainty.

A sampling-based approach for information-theoretic inspection management.

A partially supervised approach to Structural Health Monitoring is proposed, to manage the cost associated with expert inspections and maximize the value of monitoring regimes. Unlike conventional data-driven procedures, the monitoring classifier is learnt online while making predictions-negating the requirement for complete data before a system is in operation (which are rarely available). Most critically, periodic inspections are replaced (or enhanced) by an automatic inspection regime, which only queries measurements that appear informative to the evolving model of the damage-sensitive features. The result is a partially supervised Dirichlet process clustering that manages expert inspections online given incremental data. The method is verified on a simulated example and demonstrated on in situ bridge monitoring data.

Predicting local material thickness from steady-state ultrasonic wavefield measurements using a convolutional neural network.

Acoustic steady-state excitation spatial spectroscopy (ASSESS) is a full-field, ultrasonic non-destructive evaluation (NDE) technique used to locate and characterize defects in plate-like structures. ASSESS generates a steady-state, single-tone ultrasonic excitation in a structure and a scanning laser Doppler Vibrometer (LDV) measures the resulting full-field surface velocity response. Traditional processing techniques for ASSESS data rely on wavenumber domain analysis. This paper presents the alternative use of a convolutional neural network (CNN), trained using simulated ASSESS data, to predict the local plate thickness at every pixel in the wavefield measurement directly. The defect detection accuracy of CNN-based thickness predictions are shown to improve for defects of greater size, and for defects with higher thickness reductions. The CNN demonstrates the ability to predict thickness accurately in regions where Lamb wave dispersion relations are complex or unknown, such as near the boundaries of a test specimen, so long as the CNN is trained on data that accounts for these regions. The CNN also shows generalizability to ASSESS experimental data, despite an entirely simulated training dataset.

A Bayesian Method for Material Identification of Composite Plates via Dispersion Curves.

Ultrasonic guided waves offer a convenient and practical approach to structural health monitoring and non-destructive evaluation. A key property of guided waves is the fully defined relationship between central frequency and propagation characteristics (phase velocity, group velocity and wavenumber)-which is described using dispersion curves. For many guided wave-based strategies, accurate dispersion curve information is invaluable, such as group velocity for localisation. From experimental observations of dispersion curves, a system identification procedure can be used to determine the governing material properties. As well as returning an estimated value, it is useful to determine the distribution of these properties based on measured data. A method of simulating samples from these distributions is to use the iterative Markov-Chain Monte Carlo (MCMC) procedure, which allows for freedom in the shape of the posterior. In this work, a scanning-laser Doppler vibrometer is used to record the propagation of Lamb waves in a unidirectional-glass-fibre composite plate, and dispersion curve data for various propagation angles are extracted. Using these measured dispersion curve data, the MCMC sampling procedure is performed to provide a Bayesian approach to determining the dispersion curve information for an arbitrary plate. The distribution of the material properties at each angle is discussed, including the inferred confidence in the predicted parameters. The percentage errors of the estimated values for the parameters were 10-15 points larger when using the most likely estimates, as opposed to calculating from the posterior distributions, highlighting the advantages of using a probabilistic approach.

Towards the Probabilistic Analysis of Small Bowel Capsule Endoscopy Features to Predict Severity of Duodenal Histology in Patients with Villous Atrophy.

Small bowel capsule endoscopy (SBCE) can be complementary to histological assessment of celiac disease (CD) and serology negative villous atrophy (SNVA). Determining the severity of disease on SBCE using statistical machine learning methods can be useful in the follow up of patients. SBCE can play an additional role in differentiating between CD and SNVA. De-identified SBCEs of patients with CD and SNVA were included. Probabilistic analysis of features on SBCE were used to predict severity of duodenal histology and to distinguish between CD and SNVA. Patients with higher Marsh scores were more likely to have a positive SBCE and a continuous distribution of macroscopic features of disease than those with lower Marsh scores. The same pattern was also true for patients with CD when compared to patients with SNVA. The validation accuracy when predicting the severity of Marsh scores and when distinguishing between CD and SNVA was 69.1% in both cases. When the proportions of each SBCE class group within the dataset were included in the classification model, to distinguish between the two pathologies, the validation accuracy increased to 75.3%. The findings of this work suggest that by using features of CD and SNVA on SBCE, predictions can be made of the type of pathology and the severity of disease.