Inverse Design of Mechanical Metamaterials with Target Nonlinear Response via a Neural Accelerated Evolution Strategy

Text-to-Microstructure Generation Using Generative Deep Learning

Designing novel materials is greatly dependent on understanding the design principles, physical mechanisms, and modeling methods of material microstructures, requiring experienced designers with expertise and several rounds of trial and error. Although recent advances in deep generative networks have enabled the inverse design of material microstructures, most studies involve property-conditional generation and focus on a specific type of structure, resulting in limited generation diversity and poor human-computer interaction. In this study, a pioneering text-to-microstructure deep generative network (Txt2Microstruct-Net) is proposed that enables the generation of 3D material microstructures directly from text prompts without additional optimization procedures. The Txt2Microstruct-Net model is trained on a large microstructure-caption paired dataset that is extensible using the algorithms provided. Moreover, the model is sufficiently flexible to generate different geometric representations, such as voxels and point clouds. The model's performance is also demonstrated in the inverse design of material microstructures and metamaterials. It has promising potential for interactive microstructure design when associated with large language models and could be a user-friendly tool for material design and discovery.

Inverse design of Bézier curve-based mechanical metamaterials with programmable negative thermal expansion and negative Poisson's ratio via a data augmented deep autoencoder

Controlling stress and deformation induced by thermo-mechanical stimulation in high-precision mechanical systems can be achieved by mechanical metamaterials (MM) exhibiting negative thermal expansion (NTE) and negative Poisson's ratio (NPR). However, the inverse design of MM exhibiting a wide range of arbitrary target NTEs and NPRs is a challenging task due to the low design flexibility of analytical methods and parametric studies based on numerical simulation. In this study, we propose Bézier curve-based programmable chiral mechanical metamaterials (BPCMs) and a deep autoencoder-based inverse design model (DAIM) for the inverse design of BPCMs. Through iterative transfer learning with data augmentation, DAIM can generate BPCMs with a curved rib shape inaccessible with the Bézier curve, which improves the inverse design performance of the DAIM in the data sparse domain. This approach decreases the mean absolute error of NTE and NPR between the inverse design target and the numerical simulation results of inverse designed BPCMs on the data-sparse domain by 79.25% and 83.33% on average, respectively. A 3D-printed BPCM is validated experimentally and exhibits good coincidence with the target NTE and NPR. Our proposed BPCM and the corresponding inverse design framework enable the inverse design of BPCMs with NTE in the range of -1100 to 0 ppm K-1 and NPR in the range of -0.6 to -0.1. Furthermore, programmable thermal deformation modes with a fixed Poisson's ratio are realized by combining various inverse designed BPCM unit cells. BPCMs and the DAIM for their inverse design are expected to improve the mechanical robustness of high-precision mechanical systems through tunable modulation of thermo-mechanical stimulation.

Flexible sensors with zero Poisson's ratio

Flexible sensors have been developed for the perception of various stimuli. However, complex deformation, usually resulting from forces or strains from multi-axes, can be challenging to measure due to the lack of independent perception of multiaxial stimuli. Herein, flexible sensors based on the metamaterial membrane with zero Poisson's ratio (ZPR) are proposed to achieve independent detection of biaxial stimuli. By deliberately designing the geometric dimensions and arrangement parameters of elements, the Poisson's ratio of an elastomer membrane can be modulated from negative to positive, and the ZPR membrane can maintain a constant transverse dimension under longitudinal stimuli. Due to the accurate monitoring of grasping force by ZPR sensors that are insensitive to curvatures of contact surfaces, rigid robotic manipulators can be guided to safely grasp deformable objects. Meanwhile, the ZPR sensor can also precisely distinguish different states of manipulators. When ZPR sensors are attached to a thermal-actuation soft robot, they can accurately detect the moving distance and direction. This work presents a new strategy for independent biaxial stimuli perception through the design of mechanical metamaterials, and may inspire the future development of advanced flexible sensors for healthcare, human-machine interfaces and robotic tactile sensing.

Zero modes activation to reconcile floppiness, rigidity, and multistability into an all-in-one class of reprogrammable metamaterials

Existing mechanical metamaterials are typically designed to either withstand loads as a stiff structure, shape morph as a floppy mechanism, or trap energy as a multistable matter, distinct behaviours that correspond to three primary classes of macroscopic solids. Their stiffness and stability are sealed permanently into their architecture, mostly remaining immutable post-fabrication due to the invariance of zero modes. Here, we introduce an all-in-one reprogrammable class of Kagome metamaterials that enable the in-situ reprogramming of zero modes to access the apparently conflicting properties of all classes. Through the selective activation of metahinges via self-contact, their architecture can be switched to acquire on-demand rigidity, floppiness, or global multistability, bridging the seemingly uncrossable gap between structures, mechanisms, and multistable matters. We showcase the versatile generalizations of the metahinge and remarkable reprogrammability of zero modes for a range of properties including stiffness, mechanical signal guiding, buckling modes, phonon spectra, and auxeticity, opening a plethora of opportunities for all-in-one materials and devices.

Perfect circular polarization of elastic waves in solid media

Elastic waves involving mechanical particle motions of solid media can couple volumetric and shear deformations, making their manipulation more difficult than electromagnetic waves. Thereby, circularly polarized waves in the elastic regime have been little explored, unlike their counterparts in the electromagnetic regime, where their practical usage has been evidenced in various applications. Here, we explore generating perfect circular polarization of elastic waves in an isotropic solid medium. We devise a novel strategy for converting a linearly polarized wave into a circularly polarized wave by employing an anisotropic medium, which induces a so-far-unexplored coupled resonance phenomenon; it describes the simultaneous occurrence of the Fabry-Pérot resonance in one diagonal plane and the quarter-wave resonance in another diagonal plane orthogonal to the former with an exact 90° out-of-phase relation. We establish a theory explaining the involved physics and validate it numerically and experimentally. As a potential application of elastic circular polarization, we present simulation results demonstrating that a circularly polarized elastic wave can detect an arbitrarily oriented crack undetectable by a linearly polarized elastic wave.

Maximizing Triboelectric Nanogenerators by Physics-Informed AI Inverse Design

Triboelectric nanogenerators offer an environmentally friendly approach to harvesting energy from mechanical excitations. This capability has made them widely sought-after as an efficient, renewable, and sustainable energy source, with the potential to decrease reliance on traditional fossil fuels. However, developing triboelectric nanogenerators with specific output remains a challenge mainly due to the uncertainties associated with their complex designs for real-life applications. Artificial intelligence-enabled inverse design is a powerful tool to realize performance-oriented triboelectric nanogenerators. This is an emerging scientific direction that can address the concerns about the design and optimization of triboelectric nanogenerators leading to a next generation nanogenerator systems. This perspective paper aims at reviewing the principal analysis of triboelectricity, summarizing the current challenges of designing and optimizing triboelectric nanogenerators, and highlighting the physics-informed inverse design strategies to develop triboelectric nanogenerators. Strategic inverse design is particularly discussed in the contexts of expanding the four-mode analytical models by physics-informed artificial intelligence, discovering new conductive and dielectric materials, and optimizing contact interfaces. Various potential development levels of artificial intelligence-enhanced triboelectric nanogenerators are delineated. Finally, the potential of physics-informed artificial intelligence inverse design to propel triboelectric nanogenerators from prototypes to multifunctional intelligent systems for real-life applications is discussed.

Electrochemically Responsive 3D Nanoarchitectures

Responsive nanomaterials are being developed to create new unique functionalities such as switchable colors and adhesive properties or other programmable features in response to external stimuli. While many existing examples rely on changes in temperature, humidity, or pH, this study aims to explore an alternative approach relying on simple electric input signals. More specifically, 3D electrochromic architected microstructures are developed using carbon nanotube-Tin (Sn) composites that can be reconfigured by lithiating Sn with low power electric input (≈50 nanowatts). These microstructures have a continuous, regulated, and non-volatile actuation determined by the extent of the electrochemical lithiation process. In addition, this proposed fabrication process relies only on batch lithographic techniques, enabling the parallel production of thousands of 3D microstructures. Structures with a 30-97% change in open-end area upon actuation are demonstrated and the importance of geometric factors in the response and structural integrity of 3D architected microstructures during electrochemical actuation is highlighted.

High-Stroke, High-Output-Force, Fabric-Lattice Artificial Muscles for Soft Robots

Artificial muscles, providing safe and close interaction between humans and machines, are essential in soft robotics. However, their insufficient deformation, output force, or configurability usually limits their applications. Herein, this work presents a class of lightweight fabric-lattice artificial muscles (FAMs) that are pneumatically actuated with large contraction ratios (up to 87.5%) and considerable output forces (up to a load of 20 kg, force-to-weight ratio of over 250). The developed FAMs consist of a group of active air chambers that are zigzag connected into a lattice through passive connecting layers. The geometry of these fabric components is programmable to convert the in-plane lattice of FAMs into out-of-plane configurations (e.g., arched and cylindrical) capable of linear/radial contraction. This work further demonstrates that FAMs can be configured for various soft robotic applications, including the powerful robotic elbow with large motion range and high load capability, the well-fitting assistive shoulder exosuit that can reduce muscle activity during abduction, and the adaptive soft gripper that can grasp irregular objects. These results show the unique features and broad potential of FAMs for high-performance soft robots.

Physics-aware differentiable design of magnetically actuated kirigami for shape morphing

Shape morphing that transforms morphologies in response to stimuli is crucial for future multifunctional systems. While kirigami holds great promise in enhancing shape-morphing, existing designs primarily focus on kinematics and overlook the underlying physics. This study introduces a differentiable inverse design framework that considers the physical interplay between geometry, materials, and stimuli of active kirigami, made by soft material embedded with magnetic particles, to realize target shape-morphing upon magnetic excitation. We achieve this by combining differentiable kinematics and energy models into a constrained optimization, simultaneously designing the cuts and magnetization orientations to ensure kinematic and physical feasibility. Complex kirigami designs are obtained automatically with unparalleled efficiency, which can be remotely controlled to morph into intricate target shapes and even multiple states. The proposed framework can be extended to accommodate various active systems, bridging geometry and physics to push the frontiers in shape-morphing applications, like flexible electronics and minimally invasive surgery.

Unifying the design space and optimizing linear and nonlinear truss metamaterials by generative modeling

The rise of machine learning has fueled the discovery of new materials and, especially, metamaterials-truss lattices being their most prominent class. While their tailorable properties have been explored extensively, the design of truss-based metamaterials has remained highly limited and often heuristic, due to the vast, discrete design space and the lack of a comprehensive parameterization. We here present a graph-based deep learning generative framework, which combines a variational autoencoder and a property predictor, to construct a reduced, continuous latent representation covering an enormous range of trusses. This unified latent space allows for the fast generation of new designs through simple operations (e.g., traversing the latent space or interpolating between structures). We further demonstrate an optimization framework for the inverse design of trusses with customized mechanical properties in both the linear and nonlinear regimes, including designs exhibiting exceptionally stiff, auxetic, pentamode-like, and tailored nonlinear behaviors. This generative model can predict manufacturable (and counter-intuitive) designs with extreme target properties beyond the training domain.

Deep Learning in Mechanical Metamaterials: From Prediction and Generation to Inverse Design

Mechanical metamaterials are meticulously designed structures with exceptional mechanical properties determined by their microstructures and constituent materials. Tailoring their material and geometric distribution unlocks the potential to achieve unprecedented bulk properties and functions. However, current mechanical metamaterial design considerably relies on experienced designers' inspiration through trial and error, while investigating their mechanical properties and responses entails time-consuming mechanical testing or computationally expensive simulations. Nevertheless, recent advancements in deep learning have revolutionized the design process of mechanical metamaterials, enabling property prediction and geometry generation without prior knowledge. Furthermore, deep generative models can transform conventional forward design into inverse design. Many recent studies on the implementation of deep learning in mechanical metamaterials are highly specialized, and their pros and cons may not be immediately evident. This critical review provides a comprehensive overview of the capabilities of deep learning in property prediction, geometry generation, and inverse design of mechanical metamaterials. Additionally, this review highlights the potential of leveraging deep learning to create universally applicable datasets, intelligently designed metamaterials, and material intelligence. This article is expected to be valuable not only to researchers working on mechanical metamaterials but also those in the field of materials informatics.

Mechanical metamaterials and beyond

Mechanical metamaterials enable the creation of structural materials with unprecedented mechanical properties. However, thus far, research on mechanical metamaterials has focused on passive mechanical metamaterials and the tunability of their mechanical properties. Deep integration of multifunctionality, sensing, electrical actuation, information processing, and advancing data-driven designs are grand challenges in the mechanical metamaterials community that could lead to truly intelligent mechanical metamaterials. In this perspective, we provide an overview of mechanical metamaterials within and beyond their classical mechanical functionalities. We discuss various aspects of data-driven approaches for inverse design and optimization of multifunctional mechanical metamaterials. Our aim is to provide new roadmaps for design and discovery of next-generation active and responsive mechanical metamaterials that can interact with the surrounding environment and adapt to various conditions while inheriting all outstanding mechanical features of classical mechanical metamaterials. Next, we deliberate the emerging mechanical metamaterials with specific functionalities to design informative and scientific intelligent devices. We highlight open challenges ahead of mechanical metamaterial systems at the component and integration levels and their transition into the domain of application beyond their mechanical capabilities.

In Situ Activation of Snap-Through Instability in Multi-Response Metamaterials through Multistable Topological Transformation

Snap-through instability has been widely leveraged in metamaterials to attain non-monotonic responses for a specific subset of applications where conventional monotonic materials fail to perform. In the remaining more plentiful set of ordinary applications, snap-through instability is harmful, and current snapping metamaterials become inadequate because their capacity to snap cannot be suppressed post-fabrication. Here, a class of topology-transformable metamaterials is introduced to enable in situ activation and deactivation of the snapping capacity, providing a remarkable level of versatility in switching between responses from monotonic to monostable and bistable snap-through. Theoretical analysis, numerical simulations, and experiments are combined to unveil the role played by contact in the topological transformation capable of increasing the geometry incompatibility and confinement stiffness of selected architectural members. The strategy here presented for post-fabrication reprogrammability of matter and on-the-fly response switching paves the way to multifunctionality for application in multiple sectors from mechanical logic gates, and adjustable energy dissipators, to in situ adaptable sport equipment.

Micro-Scale Mechanical Metamaterial with a Controllable Transition in the Poisson's Ratio and Band Gap Formation

The ability to significantly change the mechanical and wave propagation properties of a structure without rebuilding it is currently one of the main challenges in the field of mechanical metamaterials. This stems from the enormous appeal that such tunable behavior may offer from the perspective of applications ranging from biomedical to protective devices, particularly in the case of micro-scale systems. In this work, a novel micro-scale mechanical metamaterial is proposed that can undergo a transition from one type of configuration to another, with one configuration having a very negative Poisson's ratio, corresponding to strong auxeticity, and the other having a highly positive Poisson's ratio. The formation of phononic band gaps can also be controlled concurrently which can be very useful for the design of vibration dampers and sensors. Finally, it is experimentally shown that the reconfiguration process can be induced and controlled remotely through application of a magnetic field by using appropriately distributed magnetic inclusions.

Target-Driven Design of Deep-UV Nonlinear Optical Materials via Interpretable Machine Learning

The development of a data-driven science paradigm is greatly revolutionizing the process of materials discovery. Particularly, exploring novel nonlinear optical (NLO) materials with the birefringent phase-matching ability to deep-ultraviolet (UV) region is of vital significance for the field of laser technologies. Herein, a target-driven materials design framework combining high-throughput calculations (HTC), crystal structure prediction, and interpretable machine learning (ML) is proposed to accelerate the discovery of deep-UV NLO materials. Using a dataset generated from HTC, an ML regression model for predicting birefringence is developed for the first time, which exhibits a possibility of achieving fast and accurate prediction. Essentially, crystal structures are adopted as the only known input of this model to establish a close structure-property relationship mapping birefringence. Utilizing the ML-predicted birefringence which can affect the shortest phase-matching wavelength, a full list of potential chemical compositions based on an efficient screening strategy is identified. Further, eight structures with good stability are discovered to show potential applications in the deep-UV region, owing to their promising NLO-related properties. This study provides a new insight into the discovery of NLO materials and this design framework can identify desired materials with high performances in the broad chemical space at a low computational cost.