Mahindra Rautela
YOU?
Author Swipe
View article: MORPH: PDE Foundation Models with Arbitrary Data Modality
MORPH: PDE Foundation Models with Arbitrary Data Modality Open
We introduce MORPH, a modality-agnostic, autoregressive foundation model for partial differential equations (PDEs). MORPH is built on a convolutional vision transformer backbone that seamlessly handles heterogeneous spatiotemporal datasets…
View article: Adaptively Switching Gradient Descent for Reliable PINN Training with Guarantees
Adaptively Switching Gradient Descent for Reliable PINN Training with Guarantees Open
View article: CBOL-Tuner: Classifier-pruned Bayesian optimization to explore temporally structured latent spaces for particle accelerator tuning
CBOL-Tuner: Classifier-pruned Bayesian optimization to explore temporally structured latent spaces for particle accelerator tuning Open
Complex dynamical systems, such as particle accelerators, often require complicated and time-consuming tuning procedures for optimal performance. It may also be required that these procedures estimate the optimal system parameters, which g…
View article: Time-inversion of spatiotemporal beam dynamics using uncertainty-aware latent evolution reversal
Time-inversion of spatiotemporal beam dynamics using uncertainty-aware latent evolution reversal Open
Charged particle dynamics under the influence of electromagnetic fields is a challenging spatiotemporal problem. Many high performance physics-based simulators for predicting behavior in a charged particle beam are computationally expensiv…
View article: A conditional latent autoregressive recurrent model for generation and forecasting of beam dynamics in particle accelerators
A conditional latent autoregressive recurrent model for generation and forecasting of beam dynamics in particle accelerators Open
View article: Towards latent space evolution of spatiotemporal dynamics of six-dimensional phase space of charged particle beams
Towards latent space evolution of spatiotemporal dynamics of six-dimensional phase space of charged particle beams Open
Addressing the charged particle beam diagnostics in accelerators poses a formidable challenge, demanding high-fidelity simulations in limited computational time. Machine learning (ML) based surrogate models have emerged as a promising tool…
View article: Accelerator system parameter estimation using variational autoencoded latent regression
Accelerator system parameter estimation using variational autoencoded latent regression Open
A particle accelerator is a time-varying complex system whose various components are regularly perturbed by external disturbances. The tuning of the accelerator can be a time-consuming process involving manual adjustment of multiple compon…
View article: A conditional latent autoregressive recurrent model for generation and forecasting of beam dynamics in particle accelerators
A conditional latent autoregressive recurrent model for generation and forecasting of beam dynamics in particle accelerators Open
Particle accelerators are complex systems that focus, guide, and accelerate intense charged particle beams to high energy. Beam diagnostics present a challenging problem due to limited non-destructive measurements, computationally demandin…
View article: A conditional latent autoregressive recurrent model for generation and forecasting of beam dynamics in particle accelerators
A conditional latent autoregressive recurrent model for generation and forecasting of beam dynamics in particle accelerators Open
Particle accelerators are complex systems that focus, guide, and accelerate intense charged particle beams to high energy. Beam diagnostics present a challenging problem due to limited non-destructive measurements, computationally demandin…
View article: Machine learning algorithms for delaminations detection on composites panels by wave propagation signals analysis: Review, experiences and results
Machine learning algorithms for delaminations detection on composites panels by wave propagation signals analysis: Review, experiences and results Open
Performances are a key concern in aerospace vehicles, requiring safer structures with as little consumption as possible. Composite materials replaced aluminum alloys even in primary aerospace structures to achieve higher performances with …
View article: Bayesian optimized physics-informed neural network for estimating wave propagation velocities
Bayesian optimized physics-informed neural network for estimating wave propagation velocities Open
In this paper, we propose a novel inverse parameter estimation approach called Bayesian optimized physics-informed neural network (BOPINN). In this study, a PINN solves the partial differential equation (PDE), whereas Bayesian optimization…
View article: Deep generative models for unsupervised delamination detection using guided waves
Deep generative models for unsupervised delamination detection using guided waves Open
With the rising demands for robust structural health monitoring procedures for aerospace structures, the scope of intelligent algorithms and learning techniques is expanding. Supervised algorithms have shown promising results in the field …
View article: Towards deep generation of guided wave representations for composite materials
Towards deep generation of guided wave representations for composite materials Open
Laminated composite materials are widely used in most fields of engineering. Wave propagation analysis plays an essential role in understanding the short-duration transient response of composite structures. The forward physics-based models…
View article: Real-time rapid leakage estimation for deep space habitats using exponentially-weighted adaptively-refined search
Real-time rapid leakage estimation for deep space habitats using exponentially-weighted adaptively-refined search Open
The recent accelerated growth in space-related research and development activities makes the near-term need for long-term extraterrestrial habitats evident. Such habitats must operate under continuous disruptive conditions arising from ext…
View article: Guided wave representations dataset for material property estimation and generation
Guided wave representations dataset for material property estimation and generation Open
Material property identification in composite materials is necessary for material degradation as well as non-destructive characterization. The inverse problem needs a forward simulator. Ultrasonic-guided waves are sensitive to material pro…
View article: Guided wave representations dataset for material property estimation and generation
Guided wave representations dataset for material property estimation and generation Open
Material property identification in composite materials is necessary for material degradation as well as non-destructive characterization. The inverse problem needs a forward simulator. Ultrasonic-guided waves are sensitive to material pro…
View article: Delamination prediction in composite panels using unsupervised-feature learning methods with wavelet-enhanced guided wave representations
Delamination prediction in composite panels using unsupervised-feature learning methods with wavelet-enhanced guided wave representations Open
View article: Inverse characterization of composites using guided waves and convolutional neural networks with dual-branch feature fusion
Inverse characterization of composites using guided waves and convolutional neural networks with dual-branch feature fusion Open
In this work, ultrasonic guided waves and a dual-branch version of convolutional neural networks are used to solve two different but related inverse problems, i.e., finding layup sequence type and identifying material properties. In the fo…