Search Results (32)

The goal of this study is to develop an efficient machine learning framework for designing high-hardness multi-metal nitride coatings, overcoming the limitations of traditional trial-and-error methods. The development of multicomponent metal nitride hard coatings via multi-arc ion plating remains a significant challenge due to the vast compositional search space. Although theoretical studies in macroscopic, mesoscopic, and microscopic domains exist, these often focus on idealized models and lack effective coupling across scales, leading to time-consuming and labor-intensive traditional methods. With advancements in materials genomics and data mining, machine learning has become a powerful tool in material discovery. In this work, we construct a compositional search space for multicomponent nitrides based on electronic configuration, valence electron count, electronegativity, and oxidation states of metal elements in unary nitrides. The search space is further constrained by FCC crystal structure and hardness theory. By incorporating a feature library with micro-, meso-, and macro-structural characteristics and using clustering analysis with theoretical intermediate variables, the model enriches dataset information and enhances predictive accuracy by reducing experimental errors. This model is successfully applied to design multicomponent metal nitride coatings using a literature-derived database of 233 entries. Experimental validation confirms the model’s predictions, and clustering is used to minimize experimental and data errors, yielding a strong agreement between predicted optimal molar ratios of metal elements and nitrogen and measured hardness performance. Of the 100 Vickers hardness (HV) predictions made by the model using input features like molar ratios of metal elements (e.g., Ti, Al, Cr, Zr) and atomic size mismatch, 82 exceeded the dataset’s maximum hardness, with the best sample achieving a prediction accuracy of 91.6% validated against experimental measurements. This approach offers a robust strategy for designing high-performance coatings with optimized hardness. Full article

Multi-scale thermal regulation of urban green spaces is critical for climate-adaptive planning. Addressing the limited research on key indicators and cross-scale synergies in high-density areas, this study developed an integrated framework combining multi-granularity grids and boosted regression tree (BRT) modeling to investigate nonlinear scale-dependent relationships between landscape parameters and land surface temperature (LST) in the central urban area of Shijiazhuang. Key findings: (1) Spatial heterogeneity and scale divergence: Vegetation coverage (FVC) and green space area (AREA) showed decreasing contributions at larger scales, while configuration metrics (e.g., aggregation index (AI), edge density (ED)) exhibited positive scale responses, confirming a dual mechanism with micro-scale quality dominance and macro-scale pattern regulation. (2) Threshold effects quantification: The BRT model revealed peak marginal cooling efficiency (0.8–1.2 °C per 10% FVC increment) within 30–70% FVC ranges, with minimum effective green patch area thresholds increasing from 0.6 ha (micro-scale) to 3.5 ha (macro-scale). (3) Based on multi-scale cooling mechanism analysis, a three-tier matrix optimization framework for green space strategies is established, integrating “micro-level regulation, meso-level connectivity, and macro-level anchoring”. This study develops a green space optimization paradigm integrating machine learning-driven analysis, multi-scale coupling, and threshold-based management, providing methodological tools for mitigating urban heat islands and enhancing climate resilience in high-density cities. Full article

The ability of AI to process vast datasets can enhance creativity, but its rigid knowledge base and lack of reflective thinking limit sustainable design. Generative Design Thinking (GDT) integrates human cognition and machine learning to enhance design automation. This study aims to explore the cognitive mechanisms underlying GDT and their impact on design efficiency. Using behavioral coding and quantitative analysis, we developed a three-tier cognitive model comprising a macro-cycle (knowledge acquisition and expression), meso-cycle (creative generation, intelligent evaluation, and feedback adjustment), and micro-cycle (knowledge base and model optimization). The findings reveal that increased task complexity elevates cognitive load, supporting the hypothesis that designers need to allocate more cognitive resources for complex problems. Knowledge base optimization significantly impacts design efficiency more than generative model refinement. Moreover, creative generation, evaluation, and feedback adjustment are interdependent, highlighting the importance of a dynamic knowledge base for creativity. This study challenges traditional design automation approaches by advocating for an adaptive framework that balances cognitive processes and machine capabilities. The results suggest that improving knowledge management and reducing cognitive load can enhance design outcomes. Future research should focus on developing flexible, real-time knowledge repositories and optimizing generative models for interdisciplinary and sustainable design contexts. Full article

Activity recognition combined with artificial intelligence is a vital area of research, ranging across diverse domains, from sports and healthcare to smart homes. In the industrial domain, and the manual assembly lines, the emphasis shifts to human–machine interaction and thus to human activity recognition (HAR) within complex operational environments. Developing models and methods that can reliably and efficiently identify human activities, traditionally just categorized as either simple or complex activities, remains a key challenge in the field. Limitations of the existing methods and approaches include their inability to consider the contextual complexities associated with the performed activities. Our approach to address this challenge is to create different levels of activity abstractions, which allow for a more nuanced comprehension of activities and define their underlying patterns. Specifically, we propose a new hierarchical taxonomy for human activity abstraction levels based on the context of the performed activities that can be used in HAR. The proposed hierarchy consists of five levels, namely atomic, micro, meso, macro, and mega. We compare this taxonomy with other approaches that divide activities into simple and complex categories as well as other similar classification schemes and provide real-world examples in different applications to demonstrate its efficacy. Regarding advanced technologies like artificial intelligence, our study aims to guide and optimize industrial assembly procedures, particularly in uncontrolled non-laboratory environments, by shaping workflows to enable structured data analysis and highlighting correlations across various levels throughout the assembly progression. In addition, it establishes effective communication and shared understanding between researchers and industry professionals while also providing them with the essential resources to facilitate the development of systems, sensors, and algorithms for custom industrial use cases that adapt to the level of abstraction. Full article

Unconfined compressive strength (UCS) is an important parameter of rock and soil mechanical behavior in foundation engineering design and construction. In this study, salinized frozen soil is selected as the research object, and soil GDS tests, ultrasonic tests, and scanning electron microscopy (SEM) tests are conducted. Based on the classification method of the model parameters, 2 macroscopic parameters, 38 mesoscopic parameters, and 19 microscopic parameters are selected. A machine learning model is used to predict the strength of soil considering the three-level characteristic parameters. Four accuracy evaluation indicators are used to evaluate six machine learning models. The results show that the radial basis function (RBF) has the best UCS predictive performance for both the training and testing stages. In terms of acceptable accuracy and stability loss, through the analysis of the gray correlation and rough set of the three-level parameters, the total amount and proportion of parameters are optimized so that there are 2, 16, and 16 macro, meso, and micro parameters in a sequence, respectively. In the simulation of the aforementioned six machine learning models with the optimized parameters, the RBF still performs optimally. In addition, after parameter optimization, the sensitivity proportion of the third-level parameters is more reasonable. The RBF model with optimized parameters proved to be a more effective method for predicting soil UCS. This study improves the prediction ability of the UCS by classifying and optimizing the model parameters and provides a useful reference for future research on salty soil strength parameters in seasonally frozen regions. Full article

This paper presents experimental results on the behavior of a class of glass fiber composites under low velocity impacts, in order to analyze their usage in designing low velocity impact-resistant components in car and marine industries. Also, a finite element model at the meso level (considering yarn as a compact, homogenous and isotropic material) was run with the help of Ansys Explicit Dynamics in order to point out the stages of the failure and the equivalent stress distribution on the main yarns in different layers of the composite. The composites were manufactured at laboratory scale via the laying-up and pressing method, using a quadriaxial glass fiber fabric (0°/+45°/90°/−45°) supplied by Castro Composites (Pontevedra, Spain) and an epoxy resin. The resin was a two-component resin (Biresin^® CR82 and hardener CH80-2) supplied by Sika Group (Bludenz, Austria). The mass ratio for the fabric and panel was kept in the range of 0.70–0.77. The variables for this research were as follows: the number of layers of glass fiber fabric, the impact velocity (2–4 m/s, corresponding to an impact energy of 11–45 J, respectively) and the diameter of the hemispherical impactor (Φ10 mm and Φ20 mm) made of hardened steel. The tests were performed on an Instron CEAST 9340 test machine, and at least three tests with close results are presented. We investigated the influence of the test parameters on the maximum force (F_max) measured during impact, the time to F_max and the duration of impact, t_f, all considered when the force is falling to zero again. Scanning electron microscopy and photography were used for discussing the failure processes at the fiber (micro) and panel (macro) level. At a velocity impact of 2 m/s (corresponding to an impact energy of 11 J), even the thinner panels (with two layers of quadriaxial glass fiber fabric, 1.64 mm thickness and a surface density of 3.51 kg/m²) had only partial penetration (damages on the panel face, without damage on panel back), but at a velocity impact of 4 m/s (corresponding to an impact energy of 45 J), only composite panels with six layers of quadriaxial fabric (5.25 mm thickness and a surface density of 9.89 kg/m²) presented back faces with only micro-exfoliated spots of the matrix for tests with both impactors. These results encourage the continuation of research on actual components for car and naval industries subjected to low velocity impacts. Full article

Due to its large number of advantages compared to traditional subtractive manufacturing techniques, additive manufacturing (AM) has gained increasing attention and popularity. Among the most common AM techniques is fused filament fabrication (FFF), usually referred to by its trademarked name: fused deposition modeling (FDM). This is the most efficient technique for manufacturing physical three-dimensional thermoplastics, such that FDM machines are nowadays the most common. Regardless of the 3D-printing methodology, AM techniques involve layer-by-layer deposition. Generally, this layer-wise process introduces anisotropy into the produced parts. The manufacturing procedure creates parts possessing heterogeneities at the micro (usually up to 1 mm) and meso (mm to cm) length scales, such as voids and pores, whose size, shape, and spatial distribution are mainly influenced by the so-called printing process parameters. Therefore, it is crucial to investigate their influence on the mechanical properties of FDM 3D-printed parts. This review starts with the identification of the printing process parameters that are considered to affect the micromechanical composition of FDM 3D-printed polymers. In what follows, their (negative) influence is attributed to characteristic mechanical properties. The remainder of this work reviews the state of the art in geometrical, numerical, and experimental analyses of FDM-printed parts. Finally, conclusions are drawn for each of the aforementioned analyses in view of microstructural modeling. Full article

The mechanical characteristics of rock are greatly influenced by hydrochemical corrosion. The chemical corrosion impact and deformation properties of the meso-pore structure of rock under the action of different hydrochemical solutions for the stability evaluation of rock mass engineering are of high theoretical relevance and applied value. Based on actual data, a support vector machine (SVM) rock constitutive model based on artificial bee colony algorithm (ABC) optimization is constructed in this article. The impact of porosity (chemical deterioration), confining pressure, and other aspects is thoroughly examined. It is used to mimic the triaxial mechanical behavior of rock under various hydration conditions, with high nonlinear prediction ability. Simultaneously, the statistical damage constitutive model and the ABC-SVM constitutive model are used to forecast the sample’s stress–strain curve and compare it to the experimental data. The two models’ correlation coefficients (R²), root mean square error (RMSE), and mean absolute percentage error (MAPE) are computed and examined. The correlation coefficient between the ABC-SVM constitutive model calculation results and the experimental results is found to be larger (R² = 0.998), and the error is smaller (RMSE = 0.7730, MAPE = 1.51), indicating that it has better prediction performance on the conventional triaxial constitutive relationship of rock. It is a highly promising new way of describing the rock’s constitutive connection. Full article

In the last few decades, industrial sectors such as smart manufacturing and aerospace have rapidly developed, contributing to the increase in production of more complex electronic boards based on SMT (Surface Mount Technology). The assembly phases in manufacturing these electronic products require the availability of technological solutions able to deal with many heterogeneous products and components. The small batch production and pre-production are often executed manually or with semi-automated stations. The commercial automated machines currently available offer high performance, but they are highly rigid. Therefore, a great effort is needed to obtain machines and devices with improved reconfigurability and flexibility for minimizing the set-up time and processing the high heterogeneity of components. These high-level objectives can be achieved acting in different ways. Indeed, a work station can be seen as a set of devices able to interact and cooperate to perform a specific task. Therefore, the reconfigurability of a work station can be achieved through reconfigurable and flexible devices and their hardware and software integration and control For this reason, significant efforts should be focused on the conception and development of innovative devices to cope with the continuous downscaling and increasing variety of the products in this growing field. In this context, this paper presents the design and development of a multi-mode hybrid micro-gripper devoted to manipulate and assemble a wide range of micro- and meso-SMT components with different dimensions and proprieties. It exploits two different handling technologies: the vacuum and friction. Full article

Improving scientific knowledge around the manufacturing of nanocomposites is key since their performance spreads across many applications, including those in meso/micro products. Powder metallurgy is a reliable process for producing these materials, but usually, machining postprocessing is required to achieve tight tolerances and quality requirements. When processing these materials, cutting force evolution determines the ability to control the microcutting operation toward the successful surface and part quality generation. This paper investigates cutting force and part quality generation during the micromilling of A356/Al₂O₃ aluminum nanocomposites produced via powder metallurgy. A set of micromilling experiments were carried out under various process parameters on nanocomposites with different nano-Al₂O₃ reinforcements (0–12.5 vol.%). The material’s ductility, internal porosity, and lack of interparticle bonding cause the cutting force generation to be irregular when nanoparticle reinforcements were absent or small. Reinforcement ratios higher than 2.5 vol.% strongly affect the cutting process by regularizing the milling force generation but lead to a proportionally increasing average force magnitudes. Hardening due to nano-reinforcement positively affects cutting mechanisms by reducing the plowing tendency of the cutting process, resulting in better surface quality. Therefore, a threshold on the nano-Al₂O₃ particles’ volumetric loadings enables an optimal design of these composite materials to support their micromachinability. Full article

Plant fiber-reinforced composites have the advantages of environmental friendliness, sustainability, and high specific strength and modulus. They are widely used as low-carbon emission materials in automobiles, construction, and buildings. The prediction of their mechanical performance is critical for material optimal design and application. However, the variation in the physical structure of plant fibers, the randomness of meso-structures, and the multiple material parameters of composites limit the optimal design of the composite mechanical properties. Based on tensile experiments on bamboo fiber-reinforced, palm oil-based resin composites, finite element simulations were carried out and the effect of material parameters on the tensile performances of the composites was investigated. In addition, machine learning methods were used to predict the tensile properties of the composites. The numerical results showed that the resin type, contact interface, fiber volume fraction, and multi-factor coupling significantly influenced the tensile performance of the composites. The results of the machine learning analysis showed that the gradient boosting decision tree method had the best prediction performance for the tensile strength of the composites (R² was 0.786) based on numerical simulation data from a small sample size. Furthermore, the machine learning analysis demonstrated that the resin performance and fiber volume fraction were critical parameters for the tensile strength of composites. This study provides an insightful understanding and effective route for investigating the tensile performance of complex bio-composites. Full article

While much of additive manufacturing (AM) research is focused on microstructure, material properties, and defects, there is much less research in regards to understanding how well the part coming out of the machine matches the 3D model it is based on, as well as what are the key process parameters an engineer needs to care about when they are optimizing for AM. The purpose of this study was to understand the dimensional accuracy of the electron beam powder bed fusion (EB-PBF) process using specimens of different length scales from Ti-6Al-4V. Metrology of the specimens produced was performed using fringe projection, or laser scanning, to characterize the as-built geometry. At the meso-scale, specimen geometry and hatching history play a critical role in dimensional deviation. The effect of hatching history was further witnessed at the macro-scale while also demonstrating the effects of thermal expansion in EB-PBF. These results make the case for further process optimization in terms of dimensional accuracy in order to reduce post-processing costs and flow time. Full article

The verification efficiency and precision of copper ore grade has a great influence on copper ore mining. At present, the common method for the exploration of reserves often uses chemical analysis and identification, which have high costs, long cycles, and pollution risks but cannot realize the in situ determination of the copper grade. The existing scalar spectrometric techniques generally have limited accuracy. As a vector spectrum, polarization state information is sensitive to mineral particle distribution and composition, which is conducive to high-precision detection. Taking the visible-near infrared parallel polarization reflectance spectrum data and grade data of a copper mine in Xiaoyuan village, Huaining County, Anhui Province, China, as an example, the characteristics of the parallel polarization spectra of the copper mine were analyzed. The spectra were pretreated by first-order derivative transform and wavelet denoising, and the dimensions of wavelet denoising spectra, parallel polarization spectra, and first-order derivative spectra were also reduced by principal component analysis (PCA). Three, four, and eight principal components of the three types of spectra were selected as variables. Four machine learning models, the radial basis function (RBF), support vector machine (SVM), generalized regression neural network (GRNN), and partial least squares regression (PLSR), were selected to establish the PCA parallel polarization reflectance spectrum and copper grade prediction model. The accuracy of the model was evaluated by the determination coefficient (R²) and root mean square error (RMSE). The results show that, for parallel polarization spectra, first-order derivative spectra, and wavelet denoising spectra, the PCA-SVM model has better results, with R² values of 0.911, 0.942, and 0.953 and RMSE values of 0.022, 0.019, and 0.017, respectively. This method can effectively reduce the redundancy of polarized hyperspectral data, has better model prediction ability, and provides a useful exploration for the grade analysis of hydrothermal copper deposits at meso-low temperatures. Full article

Considering that the machining of composites particularly fiber-reinforced polymer composites (FRPCs) has remained a challenge associated with their heterogeneity and anisotropic nature, damage caused by drilling operations can be considerably mitigated by following optimum cutting parameters. In this work, we numerically evaluated the effects of cutting parameters, such as feed rate and spindle speed, on the thrust force and torque during the drilling of glass-fiber-reinforced polymers (GFRPs). A meso-scale, also known as unidirectional ply-level-based finite element modeling, was employed assuming an individual homogenized lamina with transversely isotropic material principal directions. To initiate the meso-scale damage in each lamina, 3D formulations of Hashin’s failure theory were used for fiber damage and Puck’s failure theory was implemented for matrix damage onset via user subroutine VUMAT in ABAQUS. The developed model accounted for the complex kinematics taking place at the drill–workpiece interface and accurately predicted the thrust force and torque profiles as compared with the experimental results. The thrust forces for various drilling parameters were predicted with a maximum of 10% error as compared with the experimental results. It was found that a combination of lower feed rates and higher spindle speeds reduced the thrust force, which in turn minimized the drilling-induced damage, thus providing useful guidelines for drilling operations with higher-quality products. Finally, the effect of coefficient of friction was also investigated. Accordingly, a higher coefficient of friction between the workpiece and drill-bit reduced the thrust force. Full article

In Mediterranean streams and rivers in general, aquatic organisms use a specific habitat for rearing, growing, breeding, and wintering. Multiple studies have focused on this subject, but few for the specific purpose of developing suitability models that feed hydrobiological models for the analysis of flow regimes and the design of environmental flows. Therefore, this study analyzes the habitat preferences of five freshwater species of fish and mussels in the NE of the Iberian Peninsula for that purpose. We use simple decision trees and random forest (RF), a machine learning technique based on the aggregation of multiple decision trees, to develop suitability models that relate the habitat preferences of the five species—separately adults and juveniles—to different attributes of a physical habitat at the meso-scale. Selected attributes are the surface percentage of different levels of depth (0–15 cm, 15–30 cm, …, >120 cm), velocity (0–15 cm/s, 15–30 cm/s, …, >120 cm/s) and abiotic/biotic substrate (e.g., gigalithal, megalithal, detritus, phytal), and absence/presence of refuges (boulder, canopy shading, emerging vegetation, undercut banks, woody debris, roots). The models were developed in order to predict three ranks of habitat suitability: absence, presence and abundance, depending on the mentioned attributes of the mesohabitat analysed. Our study provides quantitative results concerning the correspondence between the presence and abundance of different species and habitat characteristics, confirming qualitative observations stated in previous studies. We proved now that the adult mussels of Unio genus require a minimum of 5% of sand or silt, low velocities, and undercut banks and roots; that Barbus meridionalis habitat changes considerably among seasons; that Salaria fluviatilis needs coarse substrates (megalithal, macrolithal and mesolithal) and velocities above 15 cm/s; and that the adult Squalius laietanus prefers glides and pools with depths above 60 cm and velocities below 45 cm/s, depending on the season; and that Anguilla anguilla prefers intermediate size substrates (macrolithal, mesolithal and microlithal). These results are essential for the modeling of environmental flows in rivers where these species are present. Thus, by analyzing how their physical habitat changes according to the flow regime, one can see whether the available habitat of fish and mussels increases or decreases and predict periods of danger for the species. Full article