Options
Kennedy, John
Preferred name
Kennedy, John
Research Output
Now showing 1 - 3 of 3
- PublicationInverse design of a topological phononic beam with interface modesInspired by the idea of topological mechanics and geometric phase, the topological phononic beam governed by topological invariants has seen growing research interest due to generation of a topologically protected interface state that can be characterized by geometric Zak phase. The interface mode has maximum amount of wave energy concentration at the interface of topologically variant beams with minimal losses and decaying wave energy fields away from it. The present study has developed a deep learning based autoencoder (AE) to inversely design topological phononic beam with invariants. By applying the transfer matrix method, a rigorous analytical model is developed to solve the wave dispersion relation for longitudinal and bending elastic waves. By determining the phase of the reflected wave, the geometric Zak phase is determined. The developed analytical models are used for input data generation to train the AE. Upon successful training, the network prediction is validated by finite element numerical simulations and experimental test on the manufactured prototype. The developed AE successfully predicts the interface modes for the combination of topologically variant phononic beams. The study findings may provide a new perspective for the inverse design of metamaterial beam and plate structures in solid and computational mechanics. The work is a step towards deep learning networks suitable for the inverse design of phononic crystals and metamaterials enabling design optimization and performance enhancements.
11Scopus© Citations 10 - PublicationMachine learning and deep learning in phononic crystals and metamaterials – A reviewMachine learning (ML), as a component of artificial intelligence, encourages structural design exploration which leads to new technological advancements. By developing and generating data-driven methodologies that supplement conventional physics and formula-based approaches, deep learning (DL), a subset of machine learning offers an efficient way to understand and harness artificial materials and structures. Recently, acoustic and mechanics communities have observed a surge of research interest in implementing machine learning and deep learning methods in the design and optimization of artificial materials. In this review we evaluate the recent developments and present a state-of-the-art literature survey in machine learning and deep learning based phononic crystals and metamaterial designs by giving historical context, discussing network architectures and working principles. We also explain the application of these network architectures adopted for design and optimization of artificial structures. Since this multidisciplinary research field is evolving, a summary of the future prospects is also covered. This review article serves to update the acoustics, mechanics, physics, material science and deep learning communities about the recent developments in this newly emerging research direction
2Scopus© Citations 52 - PublicationDesign and fabrication of 3D-printed composite metastructure with subwavelength and ultrawide bandgapsArchitected composite metastructures can exhibit a subwavelength ultrawide bandgap (BG) with prominent emerging applications in the structural vibration and noise control and, elastic wave manipulation. The present study implemented both forward and inverse design methods based on numerical simulations and machine learning (ML) methods, respectively to design and fabricate an architected composite metastructure exhibiting subwavelength and ultrawide BGs. The multilayer perceptron and radial basis function neural networks are developed for the inverse design of the composite metastructure and their accuracy and computation time are compared. The band structure revealed the presence of subwavelength and ultrawide BGs generated through local resonance and structural modes of the periodic composite lattice. Both in-plane and out-of-plane local resonant modes of the periodic lattice structure were responsible for inducing the BGs. The findings are confirmed by calculating numerical wave transmission curves and experiment tests on the fabricated supercell structures, utilizing 3D-printing technology. Both numerical and experimental results validate the ML prediction and the presence of subwavelength and ultrawide BG was observed. The design approach, research methodology and proposed composite metastructure will have a wide range of application in the structural vibration control and shock absorption.
12Scopus© Citations 2