ZivaHub + Deakin Research Online + DMU Figshare2026 · dataset
Sculpting Linear and Nonlinear Elastic Waves: Exploring Inverse Design Potentials — iNCMDAO 2024 Conference Paper (IISc Bangalore)<p dir="ltr">This conference contribution is a <b>peer-reviewed conference paper</b> presented by Pravinkumar Ghodake (Department of Mechanical Engineering, IIT Bombay) at the <b>1st International and 7th National Conference on Multidisciplinary Design, Analysis, and Optimization (iNCMDAO 2024)</b>, jointly organized by the <b>Indian Institute of Science (IISc), Bengaluru</b> and the <b>Aeronautic
ZivaHub + Deakin Research Online + DMU Figshare2026 · dataset
Conceptual comparison between multilayer perceptrons (MLPs) and Kolmogorov--Arnold networks (KANs) for function approximation<p dir="ltr">In the MLP schematic (left), nonlinear transformations are illustrated at the nodes using a fixed activation function. ReLU is used only as an illustrative example in the visualization. In contrast, a KAN (right) places learnable nonlinear functions on the network edges, allowing each connection to adapt its transformation.</p>
ZivaHub + Deakin Research Online + DMU Figshare2026 · dataset
Hyperparameter optimization results for the PIKAN model<p dir="ltr">The top panel shows the mean global error obtained in each trial, with the solid line indicating the best objective value achieved up to each trial. The lower panels show the corresponding error as a function of the number of hidden layers L, neurons per layer N, grid size G, polynomial order p, and learning rate $\alpha$. The color of each marker indicates the trial number, illustrat
ZivaHub + Deakin Research Online + DMU Figshare2026 · dataset
Hyperparameter optimization results for the semi-infinite-domain problem for the KAN and MLP models<p dir="ltr">Here, L denotes the number of hidden layers, N the number of neurons per layer, G the KAN grid size, p the KAN spline order, σ the activation function, and α the learning rate.</p>
ZivaHub + Deakin Research Online + DMU Figshare2026 · dataset
Spatial generalization of the proposed approach for the infinite-domain inverse problem under uniform and Gaussian sampling<p dir="ltr">The predicted fields and absolute errors for u and k are shown together with the MAE values measured inside, outside, and across the complete evaluation domain. The gray rectangle marks the training region [−5, 5] × [−5, 5] within the evaluation domain [−10, 10] × [−10, 10]. Gray circles indicate the observational points, which are sampled from the same distribution as the PDE colloca
ZivaHub + Deakin Research Online + DMU Figshare2026 · dataset
Hyperparameter optimization results for the infinite-domain problem for the MLP model<p dir="ltr">Here, L denotes the number of hidden layers, N the number of neurons per layer, σ the activation function, and α the learning rate.</p>
ZivaHub + Deakin Research Online + DMU Figshare2026 · dataset
Manufactured problem design for unbounded inverse problems<p dir="ltr">(Top) Schematic workflow illustrating the formulation process, progressing from target definition and domain specification (infinite and semi-infinite) to the generation of a manufactured solution satisfying the Poisson equation −∇ · (k ∇u) = f. (Bottom) Analytical solutions u and spatially varying coefficient fields k. The infinite-domain configuration (left) uses parameters α = 0.5,
ZivaHub + Deakin Research Online + DMU Figshare2026 · dataset
Sampling-strategy comparison for the semi-infinite-domain inverse problem<p dir="ltr">Uniform and exponential sampling are evaluated through the predicted fields, absolute errors, and MAE values measured inside, outside, and across the complete evaluation domain. The training region is [−5, 5] × [−5, 0] within the evaluation domain [−10, 10] × [−10, 0], with the top-boundary samples highlighted in blue.</p>
ZivaHub + Deakin Research Online + DMU Figshare2026 · dataset
Training evolution under different loss-weighting strategies<p dir="ltr">Columns correspond to fixed weights, a prescribed λ_PDE schedule, and the same schedule combined with adaptive weighting. Rows show the evolution of the loss weights, individual loss components (L_u, L_k, and L_PDE), and relative L₂ errors for u and k, respectively.</p>
ZivaHub + Deakin Research Online + DMU Figshare2026 · dataset
Inverse Design of Nonlinear Phononic Metamaterials for Nonlinear Wave Cloaking — iNCMDAO 2024 Conference Paper (IISc Bangalore)<p dir="ltr">This conference contribution is a <b>peer-reviewed conference paper</b> presented by Pravinkumar Ghodake (Department of Mechanical Engineering, IIT Bombay) at the <b>1st International and 7th National Conference on Multidisciplinary Design, Analysis, and Optimization (iNCMDAO 2024)</b>, jointly organized by the <b>Indian Institute of Science (IISc), Bengaluru</b> and the <b>Aeronautic
ZivaHub + Deakin Research Online2026 · dataset
Harmonic Scattering of S0 Lamb Wave — A Computational Study (ISTAM 2021 Young Scientist Award Paper)<p dir="ltr">This conference contribution is a Young Scientist Award paper presented by Pravinkumar Ghodake (Department of Mechanical Engineering, IIT Bombay) at the <b>66th Congress of the Indian Society of Theoretical and Applied Mechanics (ISTAM 2021)</b>, hosted at IIT Kharagpur. The work was submitted under the "Paper for the Young Scientist Award" category in the Solid Mechanics (SM) session
ZivaHub + Deakin Research Online2026 · dataset
Harmonic Scattering of Waves from Crossed-Thin-Rectangular Nonlinear Inclusions — NODYCON 2023 Conference Paper<p dir="ltr">This conference contribution is a research paper presented by Pravinkumar Ghodake (Department of Mechanical Engineering, IIT Bombay) at <b>NODYCON 2023</b> — the Third International Nonlinear Dynamics Conference. The work was submitted and published as a conference proceeding under the NODYCON Open Repository.</p><p dir="ltr"><br></p><p dir="ltr"><b>Title of contribution:</b> "Harmoni
ZivaHub2026 · dataset
Effect of Loss in Local Stiffness on Harmonic Scattering of Longitudinal Wave from a Quadratically Nonlinear Local Damage — ISTAM 2021 Conference Paper<p dir="ltr">This conference contribution is a research paper presented by Pravinkumar Ghodake (Department of Mechanical Engineering, IIT Bombay) at the <b>66th Congress of the Indian Society of Theoretical and Applied Mechanics (ISTAM 2021)</b>. The work derives analytical theoretical solutions to demonstrate the critical sensitivity of wave fields to local stiffness reductions caused by micro-vo
ZivaHub + Deakin Research Online2026 · dataset
Inverse Design of Periodic and Quasi-Periodic Nonlinear Mechanical Metamaterial — NODYCON 2023 Conference Paper<p dir="ltr">This conference contribution is a research paper presented by Pravinkumar Ghodake (Department of Mechanical Engineering, IIT Bombay) at <b>NODYCON 2023</b> — the Third International Nonlinear Dynamics Conference. The work was submitted and published as a conference proceeding under the NODYCON Open Repository. This paper is paired with the companion NODYCON 2023 paper "Harmonic Scatte
ZivaHub2026 · Crystal structure
Shape Optimization for the Design of Linear and Nonlinear Metamaterials to Improve Nonlinear Ultrasonic Testing — NDE 2021 Conference Talk [Video Presentation]<p dir="ltr">This conference contribution is a research presentation delivered by Pravinkumar Ghodake (Department of Mechanical Engineering, IIT Bombay) at <b>NDE 2021 — Virtual Conference & Exhibition</b>, organized by the <b>Indian Society for NDT (ISNDT)</b>, 09–11 December 2021. The work was published in the <b>e-Journal of Nondestructive Testing (eJNDT)</b>, ISSN 1435-4934, Vol. 27(4), Specia
HKU DataHub + figshare + Loughborough Research Repository + UP Research Data Repository2026 · Astronomical catalogue
Experimental Setup for Nonlinear Ultrasonic Measurements in Metallic Materials (Bespoke High-Power RF System)<p dir="ltr"><b>Experimental Setup for Nonlinear Ultrasonic Measurements in Metallic Materials</b></p><p dir="ltr">This dataset documents the bespoke experimental setup developed from scratch for investigating nonlinear wave phenomena, specifically harmonic generation and wave mixing, in metallic materials. The experiments aim to quantify early-stage micro-meso scale damage by measuring the nonlin
HKU DataHub + figshare + Loughborough Research Repository + UP Research Data Repository2026 · Astronomical catalogue
Dynamic Mode I Crack Propagation in Epoxy Material: Unpatched vs. Symmetrically Patched Configurations (Dynamic Photoelasticity)<p dir="ltr"><b>Experimental Study: Dynamic Mode I Crack Propagation in Epoxy Using Dynamic Photoelasticity</b></p><p dir="ltr">This dataset presents a series of high-speed dynamic photoelasticity images capturing Dynamic Mode I crack propagation in epoxy resin specimens. The experiments were conducted at the Indian Institute of Technology Kanpur (IIT Kanpur) to investigate the influence of symmet
figshare2026 · Astronomical catalogue
Pravinkumar Ghodake: PART II of Compilation of Verified Public Records, and Research Chronology - Semantic Scholar AI Literature Record<p dir="ltr"><b>Digital Footprint & Public Records — Part II: External Research & Documentary Records</b></p><p dir="ltr"><b>Pravinkumar Ramchandra Ghodake</b></p><p dir="ltr"><b>Section Description:</b> This section provides a structured repository of independently verifiable professional, academic, research, institutional, publication, and documentary records associated with Pravinkumar Ghodake.
figshare2026 · Astronomical catalogue
Pravinkumar Ghodake: Compilation of Verified Public Records, Digital Footprints, and Research Chronology<p dir="ltr"><b>Digital Footprint & Public Records — Part I: Academic & Research Profiles</b></p><p dir="ltr"><b>Pravinkumar Ramchandra Ghodake</b></p><p dir="ltr"><b>Section Description:</b> This section provides a structured repository of independently verifiable professional, academic, research, institutional, publication, and documentary records associated with Pravinkumar Ghodake. Each extern