Explore the vast range of titles available.

In recent years, machine learning (ML) techniques are seen to be promising tools to discover and design novel materials. However, the lack of robust inverse design approaches to identify promising candidate materials without exploring the entire design space causes a fundamental bottleneck. A general‐purpose inverse design approach is presented using generative inverse design networks. This ML‐based inverse design approach uses backpropagation to calculate the analytical gradients of an objective function with respect to design variables. This inverse design approach is capable of overcoming local minima traps by using backpropagation to provide rapid calculations of gradient information and running millions of optimizations with different initial values. Furthermore, an active learning strategy is adopted in the inverse design approach to improve the performance of candidate materials and reduce the amount of training data needed to do so. Compared to passive learning, the active learning strategy is capable of generating better designs and reducing the amount of training data by at least an order‐of‐magnitude in the case study on composite materials. The inverse design approach is compared with conventional gradient‐based topology optimization and gradient‐free genetic algorithms and the pros and cons of each method are discussed when applied to materials discovery and design problems. A general‐purpose inverse design approach using generative inverse design networks (GIDNs) is proposed. This deep neural network–based approach uses backpropagation and active learning for inverse design. It is shown that GIDNs can overcome local minima traps and be widely applied to materials discovery and design problems.

Elastography is a medical imaging technique used to measure the elasticity of tissues by comparing ultrasound signals before and after a light compression. The lateral resolution of ultrasound is much inferior to the axial resolution. Current elastography methods generally require both axial and lateral displacement components, making them less effective for clinical applications. Additionally, these methods often rely on the assumption of material incompressibility, which can lead to inaccurate elasticity reconstruction as no materials are truly incompressible. To address these challenges, a new physics‐informed deep‐learning method for elastography is proposed. This new method integrates a displacement network and an elasticity network to reconstruct the Young's modulus field of a heterogeneous object based on only a measured axial displacement field. It also allows for the removal of the assumption of material incompressibility, enabling the reconstruction of both Young's modulus and Poisson's ratio fields simultaneously. The authors demonstrate that using multiple measurements can mitigate the potential error introduced by the “eggshell” effect, in which the presence of stiff material prevents the generation of strain in soft material. These improvements make this new method a valuable tool for a wide range of applications in medical imaging, materials characterization, and beyond. ElastNet learns the Young's modulus field of a heterogeneous object based on a measured displacement field. The predicted stress tensor is calculated by the encoded elastic constitutive relation based on the strain and Young's modulus. The training procedure minimizes the unbalanced forces with a physical constraint and updates the predicted Young's modulus using backpropagation.

As natural predators, owls fly with astonishing stealth due to the serrated feather morphology that produces advantageous flow characteristics. Traditionally, these serrations are tailored for airfoil edges with simple two-dimensional patterns, limiting their effect on noise reduction while negotiating tradeoffs in aerodynamic performance. Conversely, the intricately structured wings of cicadas have evolved for effective flapping, presenting a potential blueprint for alleviating these aerodynamic limitations. In this study, we formulate a synergistic design strategy that harmonizes noise suppression with aerodynamic efficiency by integrating the geometrical attributes of owl feathers and cicada forewings, culminating in a three-dimensional sinusoidal serration propeller topology that facilitates both silent and efficient flight. Experimental results show that our design yields a reduction in overall sound pressure levels by up to 5.5 dB and an increase in propulsive efficiency by over 20% compared to the current industry benchmark. Computational fluid dynamics simulations validate the efficacy of the bioinspired design in augmenting surface vorticity and suppressing noise generation across various flow regimes. This topology can advance the multifunctionality of aerodynamic surfaces for the development of quieter and more energy-saving aerial vehicles. This study unveils a synergistic bioinspired design, seamlessly merging owl feather and cicada wing geometries into propeller configurations. Authors achieve reduction in noise by up to 5.5 dB while boosting aerodynamic efficiency by over 20% compared to current industry standards.

Neural network-based generative models have been actively investigated as an inverse design method for finding novel materials in a vast design space. However, the applicability of conventional generative models is limited because they cannot access data outside the range of training sets. Advanced generative models that were devised to overcome the limitation also suffer from the weak predictive power on the unseen domain. In this study, we propose a deep neural network-based forward design approach that enables an efficient search for superior materials far beyond the domain of the initial training set. This approach compensates for the weak predictive power of neural networks on an unseen domain through gradual updates of the neural network with active transfer learning and data augmentation methods. We demonstrate the potential of our framework with a grid composite optimization problem that has an astronomical number of possible design configurations. Results show that our proposed framework can provide excellent designs close to the global optima, even with the addition of a very small dataset corresponding to less than 0.5% of the initial training dataset size.

Atoms are the building blocks of matter that make up the world. To create new materials to meet some of civilization’s greatest needs, it is crucial to develop a technology to design materials on the atomic and molecular scales. However, there is currently no computational approach capable of designing materials atom-by-atom. In this study, we consider the possibility of direct manipulation of individual atoms to design materials at the nanoscale using a proposed method coined “Nano-Topology Optimization”. Here, we apply the proposed method to design nanostructured materials to maximize elastic properties. Results show that the performance of our optimized designs not only surpasses that of the gyroid and other triply periodic minimal surface structures, but also exceeds the theoretical maximum (Hashin–Shtrikman upper bound). The significance of the proposed method lies in a platform that allows computers to design novel materials atom-by-atom without the need of a predetermined design. The ability to design materials manipulating individual atoms with the best possible atom distributions for target properties is currently a challenge. Here the authors introduce Nano-TO, a topological based computational approach with an atom-by-atom control for materials design with desired properties.

HighlightsA machine learning-based approach is developed to predict the unknown defect locations by thermal vibration topographies of graphene sheets.Two prediction strategies are developed: an atom-based method which constructs data by atom indices, and a domain-based method which constructs data by domain discretization.Our machine learning model can achieve approximately a 90% prediction accuracy on the reserved data for testing, indicating a promising extrapolation into unseen future graphene configurations.Defects in graphene can profoundly impact its extraordinary properties, ultimately influencing the performances of graphene-based nanodevices. Methods to detect defects with atomic resolution in graphene can be technically demanding and involve complex sample preparations. An alternative approach is to observe the thermal vibration properties of the graphene sheet, which reflects defect information but in an implicit fashion. Machine learning, an emerging data-driven approach that offers solutions to learning hidden patterns from complex data, has been extensively applied in material design and discovery problems. In this paper, we propose a machine learning-based approach to detect graphene defects by discovering the hidden correlation between defect locations and thermal vibration features. Two prediction strategies are developed: an atom-based method which constructs data by atom indices, and a domain-based method which constructs data by domain discretization. Results show that while the atom-based method is capable of detecting a single-atom vacancy, the domain-based method can detect an unknown number of multiple vacancies up to atomic precision. Both methods can achieve approximately a 90% prediction accuracy on the reserved data for testing, indicating a promising extrapolation into unseen future graphene configurations. The proposed strategy offers promising solutions for the non-destructive evaluation of nanomaterials and accelerates new material discoveries.

Graphene oxide (GO) is playing an increasing role in many technologies. However, it remains unanswered how to strategically distribute the functional groups to further enhance performance. We utilize deep reinforcement learning (RL) to design mechanically tough GOs. The design task is formulated as a sequential decision process, and policy-gradient RL models are employed to maximize the toughness of GO. Results show that our approach can stably generate functional group distributions with a toughness value over two standard deviations above the mean of random GOs. In addition, our RL approach reaches optimized functional group distributions within only 5000 rollouts, while the simplest design task has 2 × 1011 possibilities. Finally, we show that our approach is scalable in terms of the functional group density and the GO size. The present research showcases the impact of functional group distribution on GO properties, and illustrates the effectiveness and data efficiency of the deep RL approach.

In recent years, the intersection of 3D printing and “smart” stimuli‐responsive materials has led to the development of 4D printing, an emerging field that is a subset of current additive manufacturing research. By integrating existing printing processes with novel materials, 4D printing enables the direct fabrication of sensors, controllable structures, and other functional devices. Compared to traditional manufacturing processes for smart materials, 4D printing permits a high degree of design freedom and flexibility in terms of printable geometry. An important branch of 4D printing concerns electroactive materials, which form the backbone of printable devices with practical applications throughout biology, engineering, and chemistry. Herein, the recent progress in the 4D printing of electroactive materials using several widely studied printing processes is reviewed. In particular, constituent materials and mechanisms for their preparation and printing are discussed, and functional electroactive devices fabricated using 4D printing are highlighted. Current challenges are also described and some of the many data‐driven opportunities for advancement in this promising field are presented. A novel field in the current landscape of additive manufacturing research is the production of stimuli‐responsive four‐dimensional (4D) materials, termed “4D printing.” Herein, recent progress in the 4D printing of electroactive materials is comprehensively reviewed. A variety of printable, electrically responsive materials and functional mechanisms are highlighted which enable a new generation of printable “smart” devices across multiple disciplines.

Elastography is an imaging technique to reconstruct elasticity distributions of heterogeneous objects. Since cancerous tissues are stiffer than healthy ones, for decades, elastography has been applied to medical imaging for noninvasive cancer diagnosis. Although the conventional strain-based elastography has been deployed on ultrasound diagnostic-imaging devices, the results are prone to inaccuracies. Model-based elastography, which reconstructs elasticity distributions by solving an inverse problem in elasticity, may provide more accurate results but is often unreliable in practice due to the ill-posed nature of the inverse problem. We introduce ElastNet, a de novo elastography method combining the theory of elasticity with a deep-learning approach. With prior knowledge from the laws of physics, ElastNet can escape the performance ceiling imposed by labeled data. ElastNet uses backpropagation to learn the hidden elasticity of objects, resulting in rapid and accurate predictions. We show that ElastNet is robust when dealing with noisy or missing measurements. Moreover, it can learn probable elasticity distributions for areas even without measurements and generate elasticity images of arbitrary resolution. When both strain and elasticity distributions are given, the hidden physics in elasticity—the conditions for equilibrium—can be learned by ElastNet.

Polycrystalline materials can be characterized by the preferred orientation of grains within a material, otherwise known as texture. It has been shown that texture can affect a wide range of mechanical properties in metallic materials, including elastic moduli, yield stress, strain hardening, and fracture toughness. Recent advances in additive manufacturing of metallic materials allow for controlling the spatial variation of texture and thus provide a path forward for controlling material properties through additive manufacturing. This paper investigates the benefits, in terms of mechanical performance, of varying texture spatially. We examine the material properties of a hole in a plate under load and use an adjoint-based gradient optimization algorithm coupled with a finite element solver. The method of adjoints allows for efficient calculation of design problems in a large variable space, reducing overall computational cost. As a first step to general texture optimization, we consider the idealized case of a pure fiber texture where the homogenized properties are transversely isotropic. In this special case, the only spatially varying design variables are the angles that describe the orientation of the homogenized material at each point within the structure. Material angles for both a spatially homogeneous and a spatially heterogeneous material are optimized for quantities of interest, such as compliance and von Mises stress. Additionally, the combined effects of elasticity tensor and material orientation on optimized structures are explored, as the additive manufacturing processes can potentially vary both. This work paves a way forward to design metallic materials with tunable mechanical properties at the microstructure level and is readily adapted to other materials.