Yes, you heard that right. Researchers at the Korea Advanced Institute of Science and Technology have developed a four-legged robot that can climb up iron and steel walls and ceilings, as described a study published in the journal Science Robotics on Wednesday. They call it MARVEL, short for Magnetically Adhesive Robot for Versatile and Expeditious Locomotion, and it only weighs about 18 pounds and isn't any larger than a tiny puppy at roughly 13 in long. MARVEL isn't the first robot that can climb walls, but unlike most others, it makes use of magnetic legs rather than wheels, grippers, suction cups, or propellers. It's also seriously dexterous, its designers say, adroitly navigating curved surfaces like that of a rusted metal storage tank, in part thanks to its innovative feet that use electro-magnets and a cutting edge, rubber-like smart material known as magnetorheological elastomers.

Yes, you heard that right. Researchers at the Korea Advanced Institute of Science and Technology have developed a four-legged robot that can climb up iron and steel walls and ceilings, as described a study published in the journal Science Robotics on Wednesday. They call it MARVEL, short for Magnetically Adhesive Robot for Versatile and Expeditious Locomotion, and it only weighs about 18 pounds and isn't any larger than a tiny puppy at roughly 13 in long. MARVEL isn't the first robot that can climb walls, but unlike most others, it makes use of magnetic legs rather than wheels, grippers, suction cups, or propellers. It's also seriously dexterous, its designers say, adroitly navigating curved surfaces like that of a rusted metal storage tank, in part thanks to its innovative feet that use electro-magnets and a cutting edge, rubber-like smart material known as magnetorheological elastomers.

This paper proposes a novel Adaptive Clustering-based Reduced-Order Modeling (ACROM) framework to significantly improve and extend the recent family of clustering-based reduced-order models (CROMs). This adaptive framework enables the clustering-based domain decomposition to evolve dynamically throughout the problem solution, ensuring optimum refinement in regions where the relevant fields present steeper gradients. It offers a new route to fast and accurate material modeling of history-dependent nonlinear problems involving highly localized plasticity and damage phenomena. The overall approach is composed of three main building blocks: target clusters selection criterion, adaptive cluster analysis, and computation of cluster interaction tensors. In addition, an adaptive clustering solution rewinding procedure and a dynamic adaptivity split factor strategy are suggested to further enhance the adaptive process. The coined Adaptive Self-Consistent Clustering Analysis (ASCA) is shown to perform better than its static counterpart when capturing the multi-scale elasto-plastic behavior of a particle-matrix composite and predicting the associated fracture and toughness. Given the encouraging results shown in this paper, the ACROM framework sets the stage and opens new avenues to explore adaptivity in the context of CROMs.

We describe an approach for empirical modeling of steel phase kinetics based on symbolic regression and genetic programming. The algorithm takes processed data gathered from dilatometer measurements and produces a system of differential equations that models the phase kinetics. Our initial results demonstrate that the proposed approach allows to identify compact differential equations that fit the data. The model predicts ferrite, pearlite and bainite formation for a single steel type. Martensite is not yet included in the model. Future work shall incorporate martensite and generalize to multiple steel types with different chemical compositions.

The application of machine learning to predicting the properties of small and large discrete (single) molecules and complex materials (polymeric, extended or mixtures of molecules) has been increasing exponentially over the past few decades. Unlike physics-based and rule-based computational systems, machine learning algorithms can learn complex relationships between physicochemical and process parameters and their useful properties for an extremely diverse range of molecular entities. Both the breadth of machine learning methods and the range of physical, chemical, materials, biological, medical and many other application areas have increased markedly in the past decade. This Account summarises three decades of research into improved cheminformatics and machine learning methods and their application to drug design, regenerative medicine, biomaterials, porous and 2D materials, catalysts, biomarkers, surface science, physicochemical and phase properties, nanomaterials, electrical and optical properties, corrosion and battery research. Science has always been fascinated by change, uncovering new aspects of Nature and finding useful ways to exploit them to meet global challenges. The rate of change is accelerating, with average time between innovations decreasing exponentially (Figure 1). Computational molecular design prior to 1990 was focused on the use of computationally expensive physics-based methods like molecular modelling, molecular mechanics, molecular dynamics and quantum chemistry. The quantitative structure–activity relationship (QSAR) methods, developed by Hansch and Fujita in the 1960s, were based on the observation that changes in the constitution of small organic molecules generated a corresponding change in their biological activities. Regression methods were used to find relationships between structure, encoded by mathematical entities called descriptors or features, and biological properties of small organic molecules, also numerically encoded. QSAR use was limited to modelling of small data sets of molecules with similar scaffolds, with the primary aim of understanding the molecular basis for drug (or agrochemical) action. As they were not mechanism- or physics-based, their empirical nature created doubt as to their efficacy, the question of when correlation means causation (still an important issue), and lack of data were major barriers to their wider adoption. After that time, technological developments involving automation, computational power, algorithms, synthesis and informatics have maintained this exponential acceleration.

Numerical analysis methods, such as Finite Element Analysis (FEA), are typically used to conduct stress analysis of various structures and systems for which it is impractical or hard to determine an analytical solution. Researchers commonly use FEA methods to evaluate the design, safety and maintenance of different structures in various fields, including aerospace, automotive, architecture and civil structural systems. The current workflow for FEA applications includes: (i) modeling the geometry and its components, (ii) specifying material properties, boundary conditions, meshing, and loading, (iii) dynamic analysis, which may be time-consuming based on the complexity of the model. The time requirement constraint and the complexity of the current FEA workflow make it impractical for real-time or near real-time applications, such as in the aftermath of a disaster or during extreme disruptive events that require immediate corrections to avoid catastrophic failures. Based on the steps of FEA described above, performing a complete stress analysis with conventional FEA has a high computational cost.

The chimp optimization algorithm (ChOA) is a hunting-based model and can be utilized as a set of optimization rules to tackle optimization problems. Although ChOA has shown promising results on optimization functions, it suffers from a slow convergence rate and low exploration capability. Therefore, in this paper, a modified ChOA is proposed to improve the exploration and exploitation capabilities of the ChOA. This improvement is performed using greedy search and opposition-based learning (OBL), respectively. In order to investigate the efficiency of the OBLChOA, the OBLChOA's performance is evaluated by twenty-three standard benchmark functions, ten suit tests of IEEE CEC06-2019, randomly generated landscape, and twelve real-world Constrained Optimization Problems (IEEE COPs-2020) from a variety of engineering fields, including industrial chemical producer, power system, process design and synthesis, mechanical design, power-electronic, and livestock feed ration.

In South Korea, these sleepless nights happen in many places because of the noise from upstairs neighbors. Living in the apartment units means dealing with a level of noise from the neighborhood on a daily basis. The Korea Institute of Civil Engineering and Building Technology has announced a new approach for predicting the footstep sounds of upstairs residents using a convolutional neural network (CNN) model based on vibration signals. The CNN models are widely applied in computer vision tasks. The vibration sensors are designed to be installed on the wall and floor slab of a residential building to monitor footstep-induced vibration in real–time.

The accurate prediction of physicochemical properties of chemical compounds in mixtures (such as the activity coefficient at infinite dilution $\gamma_{ij}^\infty$) is essential for developing novel and more sustainable chemical processes. In this work, we analyze the performance of previously-proposed GNN-based models for the prediction of $\gamma_{ij}^\infty$, and compare them with several mechanistic models in a series of 9 isothermal studies. Moreover, we develop the Gibbs-Helmholtz Graph Neural Network (GH-GNN) model for predicting $\ln \gamma_{ij}^\infty$ of molecular systems at different temperatures. Our method combines the simplicity of a Gibbs-Helmholtz-derived expression with a series of graph neural networks that incorporate explicit molecular and intermolecular descriptors for capturing dispersion and hydrogen bonding effects. We have trained this model using experimentally determined $\ln \gamma_{ij}^\infty$ data of 40,219 binary-systems involving 1032 solutes and 866 solvents, overall showing superior performance compared to the popular UNIFAC-Dortmund model. We analyze the performance of GH-GNN for continuous and discrete inter/extrapolation and give indications for the model's applicability domain and expected accuracy. In general, GH-GNN is able to produce accurate predictions for extrapolated binary-systems if at least 25 systems with the same combination of solute-solvent chemical classes are contained in the training set and a similarity indicator above 0.35 is also present. This model and its applicability domain recommendations have been made open-source at https://github.com/edgarsmdn/GH-GNN.

Data-driven models are central to scientific discovery. In efforts to achieve state-of-the-art model accuracy, researchers are employing increasingly complex machine learning algorithms that often outperform simple regressions in interpolative settings (e.g. random k-fold cross-validation) but suffer from poor extrapolation performance, portability, and human interpretability, which limits their potential for facilitating novel scientific insight. Here we examine the trade-off between model performance and interpretability across a broad range of science and engineering problems with an emphasis on materials science datasets. We compare the performance of black box random forest and neural network machine learning algorithms to that of single-feature linear regressions which are fitted using interpretable input features discovered by a simple random search algorithm. For interpolation problems, the average prediction errors of linear regressions were twice as high as those of black box models. Remarkably, when prediction tasks required extrapolation, linear models yielded average error only 5% higher than that of black box models, and outperformed black box models in roughly 40% of the tested prediction tasks, which suggests that they may be desirable over complex algorithms in many extrapolation problems because of their superior interpretability, computational overhead, and ease of use. The results challenge the common assumption that extrapolative models for scientific machine learning are constrained by an inherent trade-off between performance and interpretability.