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.

De-icing performance evolution with increasing hydrophobicity by regulating surface topography.

It is of great significance to grasp the role of surface topography in de-icing, which however remains unclear yet. Herein, four textured surfaces are developed by regulating surface topography while keeping surface chemistry and material constituents same. Specifically, nano-textures are maintained and micro-textures are gradually enlarged. The resultant ice adhesion strength is proportional to a topography parameter, i.e. areal fraction of the micro-textures, owing to the localized bonding strengthening, which is verified by ice detachment simulation using finite element method. Moreover, the decisive topography parameter is demonstrated to be determined by the interfacial strength distribution between ice and test surface. Such parameters vary from paper to paper due to different interfacial strength distributions corresponding to respective situations. Furthermore, since hydrophobic and de-icing performance may rely on different topography parameters, there is no certain relationship between hydrophobicity and de-icing.

The role of surface topography in de-icing is verified to be determined by the interfacial strength distribution between ice and surface experimentally and numerically, unveiling the relationship between hydrophobicity and de-icing.

Mapping stress inside living cells by atomic force microscopy in response to environmental stimuli.

The response of cells to environmental stimuli, under either physiological or pathological conditions, plays a key role in determining cell fate toward either adaptive survival or controlled death. The efficiency of such a feedback mechanism is closely related to the most challenging human diseases, including cancer. Since cellular responses are implemented through physical forces exerted on intracellular components, more detailed knowledge of force distribution through modern imaging techniques is needed to ensure a mechanistic understanding of these forces. In this work, we mapped these intracellular forces at a whole-cell scale and with submicron resolution to correlate intracellular force distribution to the cytoskeletal structures. Furthermore, we visualized dynamic mechanical responses of the cells adapting to environmental modulations in situ. Such task was achieved by using an informatics-assisted atomic force microscope (AFM) indentation technique where a key step was Markov-chain Monte Carlo optimization to search for both the models used to fit indentation force-displacement curves and probe geometry descriptors. We demonstrated force dynamics within cytoskeleton, as well as nucleoskeleton in living cells which were subjected to mechanical state modulation: myosin motor inhibition, micro-compression stimulation and geometrical confinement manipulation. Our results highlight the alteration in the intracellular prestress to attenuate environmental stimuli; to involve in cellular survival against mechanical signal-initiated death during cancer growth and metastasis; and to initiate cell migration.

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.

Deep-learning-based inverse design of three-dimensional architected cellular materials with the target porosity and stiffness using voxelized Voronoi lattices.

Architected cellular materials are a class of artificial materials with cellular architecture-dependent properties. Typically, designing cellular architectures paves the way to generate architected cellular materials with specific properties. However, most previous studies have primarily focused on a forward design strategy, wherein a geometry is generated using computer-aided design modeling, and its properties are investigated experimentally or via simulations. In this study, we developed an inverse design framework for a disordered architected cellular material (Voronoi lattices) using deep learning. This inverse design framework is a three-dimensional conditional generative adversarial network (3D-CGAN) trained based on supervised learning using a dataset consisting of voxelized Voronoi lattices and their corresponding relative densities and Young's moduli. A well-trained 3D-CGAN adopts variational sampling to generate multiple distinct Voronoi lattices with the target relative density and Young's modulus. Consequently, the mechanical properties of the 3D-CGAN generated Voronoi lattices are validated through uniaxial compression tests and finite element simulations. The inverse design framework demonstrates potential for use in bone implants, where scaffold implants can be automatically generated with the target relative density and Young's modulus.

Effect of Punch Surface Microtexture on the Microextrudability of AA6063 Micro Backward Extrusion.

To apply conventional forming processes to microscale processing, the influence of size effects caused by material properties and friction effects must be considered. Herein, the effects of tool surface properties, such as punch surface texture, on microextrusion properties, such as extrusion force, product shape, and product microstructure, were investigated using AA6063 billets as test pieces. Millimeter-scale, microscale, and nanoscale textures were fabricated on the punch surfaces. Punch texturing was conducted by electrical discharge machining or polishing or using a laser process. The extrusion force increased rapidly as the stroke progressed for all punch textures. Comparing the product shapes, the smaller the texture size, the lower the adhesion and the longer the backward extrusion length. The results of material analysis using electron backscatter diffraction show that material flowability is improved, and more strain is uniformly applied when a nanoscale-textured punch is used. By contrast, when a mirror punch was used, material flowability decreased, and strain was applied non-uniformly. Therefore, by changing the surface properties of the punch, the tribology between the tool and material can be controlled, and formability can be improved.

Topological alternation from structurally adaptable to mechanically stable crosslinked polymer.

Stimuli-responsive polymers with complicated but controllable shape-morphing behaviors are critically desirable in several engineering fields. Among the various shape-morphing materials, cross-linked polymers with exchangeable bonds in dynamic network topology can undergo on-demand geometric change via solid-state plasticity while maintaining the advantageous properties of cross-linked polymers. However, these dynamic polymers are susceptible to creep deformation that results in their dimensional instability, a highly undesirable drawback that limits their service longevity and applications. Inspired by the natural ice strategy, which realizes creep reduction using crystal structure transformation, we evaluate a dynamic cross-linked polymer with tunable creep behavior through topological alternation. This alternation mechanism uses the thermally triggered disulfide-ene reaction to convert the network topology - from dynamic to static - in a polymerized bulk material. Thus, such a dynamic polymer can exhibit topological rearrangement for thermal plasticity at 130°C to resemble typical dynamic cross-linked polymers. Following the topological alternation at 180°C, the formation of a static topology reduces creep deformation by more than 85% in the same polymer. Owing to temperature-dependent selectivity, our cross-linked polymer exhibits a shape-morphing ability while enhancing its creep resistance for dimensional stability and service longevity after sequentially topological alternation. Our design enriches the design of dynamic covalent polymers, which potentially expands their utility in fabricating geometrically sophisticated multifunctional devices.

Light-Induced Topological Patterning toward 3D Shape-Reconfigurable Origami.

Shape-reconfigurable materials are crucial in many engineering applications. However, because of their isotropic deformability, they often require complex molding equipment for shaping. A polymeric origami structure that follows predetermined deformed and non-deformed patterns at specific temperatures without molding is demonstrated. It is constructed with a heterogeneous (dynamic and static) network topology via light-induced programming. The corresponding spatio-selective thermal plasticity creates varied deformability within a single polymer. The kinematics of site-specific deformation allows guided origami deployment in response to external forces. Moreover, the self-locking origami can fix its geometry in specific states without pressurization. These features enable the development of shape-reconfigurable structures that undergo on-demand geometry changes without requiring bulky or heavy equipment. The concept enriches polymer origamis, and could be applied with other polymers having similar chemistries. Overall, it is a versatile material for artificial muscles, origami robotics, and non-volatile mechanical memory devices.

Effect of Punch Surface Grooves on Microformability of AA6063 Backward Microextrusion.

In order to apply conventional forming processes at the micro scale, the size effects caused by material properties and frictional effects must be taken into account. In this research, the effects of tool surface properties such as punch surface grooves on microextrudability, assessed using extrusion force, shape of the extrusion, and Vickers hardness, were investigated using an AA6063 billet. Microscale grooves of 5 to 10 µm were fabricated on the punch surface. The extrusion force increased rapidly as the stroke progressed for all the grooves. Comparing the product geometries showed that, the smaller the groove size, the lower the adhesion and the longer the backward extrusion length. The results of material analysis using EBSD showed that a 5 µm groove depth punch improved the material flowability and uniformly introduced more strain. On the other hand, material flowability was reduced and strain was applied nonuniformly when a mirror-finish tool was used. Therefore, the tribology between the tool and the material was controlled by changing the surface properties of the punch to improve formability.

Mechanomics Biomarker for Cancer Cells Unidentifiable through Morphology and Elastic Modulus.

Cellular mechanical properties are potential cancer biomarkers used for objective cytology to replace the current subjective method relying on cytomorphology. However, heterogeneity among intra/intercellular mechanics and the interplay between cytoskeletal prestress and elastic modulus obscured the difference detectable between malignant and benign cells. In this work, we collected high density nanoscale prestress and elastic modulus data from a single cell by AFM indentation to generate a cellular mechanome. Such high dimensional mechanome data was used to train a malignancy classifier through machine learning. The classifier was tested on 340 single cells of various origins, malignancy, and degrees of similarity in morphology and elastic modulus. The classifier showed instrument-independent robustness and classification accuracy of 89% with an AUC-ROC value of 93%. A signal-to-noise ratio 8 times that of the human-cytologist-based morphological method was also demonstrated, in differentiating precancerous hyperplasia cells from normal cells derived from the same lung cancer patient.

Multiscale analysis of mechanical behavior of multilayer steel structures fabricated by wire and arc additive manufacturing.

The mechanical behavior of multilayer steel structures fabricated via wire and arc additive manufacturing (WAAM) has been investigated from the multiscale perspective. The multimaterial WAAM approach can control a heterogeneous structure and improve its mechanical properties. In this study, WAAM equipment based on plasma arc welding was used to fabricate two pairs of single- and duplex-phase multilayer steel structures using austenitic and martensitic stainless steel wires. The heterogeneity of these structures was characterized through micro-indentation tests. In addition, tensile tests of the multilayer structures were conducted to evaluate the effect of heterogeneity on macroscopic material properties. The deformation behavior of the heterogeneous multilayer steel structures was investigated by comparison with the finite element simulations of tensile tests in which the finite element models were created according to the estimated local elastoplastic properties from the results of micro-indentation tests. The micro-indentation tests revealed that the local mechanical properties significantly change during WAAM in cases where martensitic stainless steel wire was used. Additionally, strain-induced transformation plasticity was particularly observed in duplex cases, caused by the metastable austenite phase formed according to the thermal history and through the mixing of alloy elements. Thus, the heterogeneity of the multilayer steel structures became more complicated than its design, and consequently, its macroscopic mechanical properties exceeded the upper and lower bounds of a micromechanic estimation. The results show the potential to fabricate a structure having a unique mechanical behavior via the multimaterial WAAM approach.

Stress mapping reveals extrinsic toughening of brittle carbon fiber in polymer matrix.

We conducted an in situ study on CFRP fracturing process using atomic-force-microscopy-based stress-sensitive indentation. Tensile stress distribution during fracture initiation and propagation was directly observed quantitatively. It led to a discovery that previously believed catastrophic fracture of individual carbon fiber develops in a controllable manner in the polymer matrix, exhibiting 10 times increase of fracture toughness. Plastic deformation in crack-bridging polymer matrix was accounted for the toughening mechanism. The model was applied to explain low temperature strength weakening of CFRP bulk material when matrix plasticity was intentionally 'shut down' by cryogenic cooling.

Stress dependence of indentation modulus for carbon fiber in polymer composite.

Elastic modulus measured through atomic force microscopy (AFM)-based indentation on single carbon fiber (CF) is found with dependence on lateral applied stress. An in situ indentation experiment inside a high-resolution transmission electron microscope was performed to quantitatively understand this phenomenon by observing microstructure change in the indented area. Change of graphitic basal plane misalignment angle during indentation was linked to a continuous change of modulus with the help of finite element simulation. The established relationship between modulus and indentation force was further used to calculate residual stress distribution in CF imbedded in a CF reinforced polymer composite using the AFM indentation technique. The stress-induced formation of nanoscale defects in the CF and their transformation into fracture were directly characterized.

Relation extraction with weakly supervised learning based on process-structure-property-performance reciprocity.

In this study, we develop a computer-aided material design system to represent and extract knowledge related to material design from natural language texts. A machine learning model is trained on a text corpus weakly labeled by minimal annotated relationship data (~100 labeled relationships) to extract knowledge from scientific articles. The knowledge is represented by relationships between scientific concepts, such as {annealing, grain size, strength}. The extracted relationships are represented as a knowledge graph formatted according to design charts, inspired by the process-structure-property-performance (PSPP) reciprocity. The design chart provides an intuitive effect of processes on properties and prospective processes to achieve the certain desired properties. Our system semantically searches the scientific literature and provides knowledge in the form of a design chart, and we hope it contributes more efficient developments of new materials.