Search Results (106)

This paper focuses on enhancing the accuracy and efficiency of bus travel speed prediction by improving the optimization process for deep learning model parameters. Existing intelligent optimization algorithms often suffer from slow convergence and substantial errors when tuning parameters for such predictive tasks. To mitigate these shortcomings, this study presents a new predictive framework that synergizes an Improved Atom Search Optimization (IASO) algorithm with a Bidirectional Gated Recurrent Unit (BiGRU) network. The EASO algorithm is developed through three principal modifications: (1) population initialization using a Logistic-Tent composite chaotic map to enhance diversity and initial quality; (2) incorporation of a hybrid operator merging refraction opposition-based learning and Cauchy mutation to broaden the search around promising solutions and alleviate issues of local stagnation and early convergence; and (3) implementation of an adaptive variable spiral search to recalibrate the position update rule, thereby improving the trade-off between extensive exploration and intensive exploitation. Based on the analysis of bus travel speed determinants, the IASO algorithm is applied to optimize the hyperparameters of the BiGRU network, culminating in the proposed IASO-BiGRU predictive model. Validation tests indicate that the devised IASO algorithm shows improved performance in certain aspects compared to several contemporary intelligent optimization techniques in terms of solution accuracy and convergence efficiency. Under the specific experimental conditions of this study, the IASO-BiGRU model achieves MAE, RMSE, and MAPE values of 1.62, 1.80, and 6.70%, respectively, corresponding to an improvement of 1.91–7.56% compared to the baseline models tested. These findings offer valuable data support and a decision-making foundation for bus operation scheduling and passenger travel planning. Full article

The search for new antibacterial agents is an important task due to the emergence of resistance to widely used drugs. Bromine-, chlorine-, and nitro-substituted phenyl ring azomethines with long alkyl chains (C₁₂, C₁₄, C₁₆, and C₁₈) were synthesized and characterized using several experimental methods (NMR and IR spectroscopy, elemental analysis, mass spectrometry). Antibacterial and antifungal activity was tested on several cultures; the synthesized compounds show activity at the level of some commercial antiseptics. Lipophilicity (an important descriptor for predicting biological properties) of the experimentally synthesized and isomeric molecules was determined by three different approaches: quantum chemistry, machine learning (GraphormerLogP model), and an atom contribution model (RDKit library). The quantum-chemical method can account for any spatial arrangements and can be considered the most accurate of the approaches used, but it requires significant computational time. The atom contribution model is the fastest of the methods used, but it gives underestimated results, and different isomers have exactly the same values, in contrast to the quantum chemistry results. Machine learning-based methods (GraphormerLogP) demonstrate acceptable accuracy, sensitivity to isomerism, and orders-of-magnitude higher throughput, making them an optimal tool for high-throughput screening. Full article

This study proposes a multi-level performance margin modeling and belief reliability framework for redundant systems. Starting from system performance, a “performance–margin–reliability” linkage is established by defining the performance and margin of multi-level redundant systems and deriving performance, margin, and metric equations that account for failures. For complex redundant systems, a hierarchical Behavior Interaction Priority (BIP) modeling approach is developed to explicitly represent the normal and failure states of atomic component models. The effects of redundant components on the overall system are transformed into variations of performance parameters, enabling quantitative analysis of redundancy mechanisms. This paper proposes a boundary search algorithm for pruning optimization, which breaks through the computational bottleneck of non-analytic threshold sets in high-dimensional topological spaces. A case study on a power supply system with multi-level structural redundancy is conducted. Based on the proposed method, a performance-margin model of the redundant power supply system is constructed, critical states are analyzed, and system reliability is calculated. The results verify the effectiveness of the proposed margin-equation formulation and solution algorithm, offering practical guidance for reliability design of redundant systems. Full article

Distributed energy resources (DERs) can improve the performance of radial distribution systems. The nonlinear power flow constraints, multi-objective trade-offs, and network reconfiguration scenarios for DER placement and sizing call for the formulation of optimization problems. Most of the times optimization algorithms suffer from premature convergence and poor exploration-exploitation balance. These problems exhibit an inherent internal structural symmetry. In order to overcome the above problem, this study uses the Multi-Objective Archimedes Optimization Algorithm (MAOA) to optimally allocate DERs in the Radial Distribution Networks (RDNs), moreover the performance of the proposed MAOA is compared with the other well established algorithms including Particel Swarm Optimization (PSO), Whale Optimization Algorithm (WOA), Shuffled Frog Leaping Algorithm (SFLA), Atom Search Optimization (ASO), and Butterfly Optimization Algorithm (BOA) on the IEEE-33 RDN. The comparison is made for the four cases (S1: DER Only), (S2—Network Reconfiguration Only), (S3—DER Followed by Reconfiguration), and (S4—Reconfiguration Followed by DER) considering factors like voltage profile, network reconfiguration, active and reactive power loss reduction, carbon emission DER utilization and Cost reduction. The MAOA is observed to provide better results among all the other benchmark algorithms. In S3, the active power loss is reduced by 68.41%, whereas the reactive power loss is reduced by 57.44% and the MAOA algorithm improves the voltage by 3.98%. The minimum voltage of the network is also improved by 6.28%. The algorithm improves convergence with a percentage of 18.50% enhancing the system’s operational symmetry and stability, while satisfying all constraints. At Bus 3 and Bus 6 of IEEE-33 bus radial distribution network (Baran–Wu test system), DG capacity is allocated to be 3.8 MW and 2.1 MW, respectively. Full article

Heterogeneous remote sensing image change detection (Hete-CD) holds significant research value in military and civilian fields. The existing methods often rely on expert experience to design fixed deep network architectures for cross-modal feature alignment and fusion purposes. However, when faced with diverse land cover types, these methods often lead to blurred change boundaries and structural distortions, resulting in significant performance degradations. To address this, we propose an adaptive adversarial learning-based heterogeneous remote sensing image change detection method based on the differentiable filter combination search (DFCS) strategy to provide enhanced generalizability and dynamic learning capabilities for diverse scenarios. First, a fully reconfigurable self-learning discriminator is designed to dynamically synthesize the optimal convolutional architecture from a library of atomic filters containing basic operators. This provides highly adaptive adversarial supervision to the generator, enabling joint dynamic learning between the generator and discriminator. To further mitigate modality differences in the input stage, we integrate a feature fusion module based on the Gabor and local normalized cross-correlation (G-LNCC) to extract modality-invariant texture and structure features. Finally, a geometric structure-based collaborative supervision (GSCS) loss function is constructed to impose fine-grained constraints on the change map from the perspectives of regions, boundaries, and structures, thereby enforcing physical properties. Comparative experimental results obtained on five public Hete-CD datasets show that our method achieves the best F1 values and overall accuracy levels, especially on the Gloucester I and Gloucester II datasets, achieving F1 scores of 93.7% and 95.0%, respectively, demonstrating the strong generalizability of our method in complex scenarios. Full article

Low-viscosity epoxy-containing diluents are used to reduce the initial viscosity of highly filled, wear-resistant epoxy systems and to improve filler wetting and dispersion. This study determined physical parameters by an atomic-increment approach and electronic descriptors using the Parametric Method 3 (PM3) semi-empirical method. Clear relationships were established between the effective molar cohesion energy and the solubility parameter with van der Waals volume. Linear dependencies were also obtained between the diluent surface tension and spreading coefficients on model high-hardness fillers, including silicon carbide, boron carbide, and normal corundum. The activity of epoxy diluents depends on the lowest unoccupied molecular orbital energy. These diluents influence processing and the final physical and mechanical properties of composites, making their selection critical for strength, hardness, and wear resistance. Computational analysis enables prediction of diluent behavior, reducing experimental time and cost. Integrating physical and quantum-chemical data into epoxy diluent design accelerates the search for optimal components and improves production of durable, high-performance epoxy composites. Full article

This study aims to optimize the variables of the gas metal arc welding (GMAW)-based wire arc additive manufacturing (WAAM) process namely, wire feed speed (WFS), voltage (V), and travel speed (TS), to achieve the desired bead geometries, specifically bead width (BW), and bead height (BH) on a mild steel substrate. The selection of WAAM parameters significantly influences the characteristics of multi-layer structures in terms of bead geometry. By optimizing these variables, the research seeks to enhance bead geometry properties, thereby improving the overall performance of the WAAM process. Single-layer depositions were performed using TM-B6 metallic wire using Box–Behnken design methodology. Multivariable regression equations were formulated to establish relationships between design variables and their corresponding responses, with their validity assessed through ANOVA. For both BW and BH responses, the R² and adjusted R² values were found to be close to unity, indicating excellent model fitness. The results demonstrate the high accuracy of the models, enabling effective analysis of the influence of process parameters on weld bead geometry and accurate prediction of bead dimensions across the design space. The main effects plot illustrates how WFS, V, and TS affect bead width and bead height. Atomic Search Optimization (ASO) was employed to determine optimal parameter combinations. An objective function with equal weightage (0.5) for BH and BW was formulated, resulting in optimized values of BW and BH (4.01 mm and 5.86 mm, respectively) at WFS: 13 m/min, TS: 10 mm/s, and V: 20 V. The obtained findings confirm the high accuracy of the models and their effectiveness in analyzing and optimizing WAAM process parameters. Full article

Efficient scheduling is critical for the success of any organization. Researchers have proposed numerous strategies for addressing various scheduling problems. The hybrid flow shop (HFS) scheduling is a complex and NP-hard problem that arises in many manufacturing and service industries. This work introduces an optimization technique that utilizes atomic orbitals to address issues in HFS scheduling. Our objective is to reduce makespan (Cmax). Makespan minimization is critical for improving productivity and resource utilization. The standard atomic orbital search optimization algorithm (AOSOA) is hybridized with constructive heuristics to enhance solution quality. The scheduling problem of an electrical panel board manufacturing industry is solved using the hybrid AOSOA (HAOSOA). The results were better than those previously reported. A variety of random test situations of varying sizes and configurations were devised to assess the efficacy of the suggested algorithm. The proposed algorithm’s outcomes were compared against well-known algorithms discussed in the literature. Friedman and Wilcoxon test results indicate that the proposed methodology improves the solution quality in each test instance compared to all the metaheuristics used for comparison. The performance of the proposed algorithm is also evaluated using benchmark problems from the literature. In the first test, the algorithm has a rank value of 1, indicating it performs better than each of the comparing algorithms. In the second test, it is able to find the best makespan for 65 of the 77 problems. Full article

Particle Swarm Optimization (PSO) is a metaheuristic optimization technique based on population behavior, inspired by the movement of a flock of birds or a school of fish. In this method, particles move in a search space to find the global minimum of an objective function. In this work, a modified PSO algorithm written in Fortran 90 is proposed. The optimized structures obtained with this algorithm are compared with those obtained using the basin-hopping (BH) method written in Python (3.10), and complemented with density functional theory (DFT) calculations using the Gaussian 09 software. Additionally, the results are compared with the structural parameters reported from single crystal X-ray diffraction data for carbon clusters ${\mathrm{C}}_n$(n = 3–5), and tungsten–oxygen clusters, ${\mathrm{WO}}_n^{m-}$(n = 4–6, $m=2,4,6$). The PSO algorithm performs the search for the minimum energy of a harmonic potential function in a hyperdimensional space $\in {\mathbb{R}}^{3N}$ (where N is the number of atoms in the system), updating the global best position ( $g_{best}$) and local best position ( $p_{best}$), as well as the velocity and position vectors for each swarm cluster. A good approximation of the optimized structures and energies of these clusters was obtained, compared to the geometric optimization and single-point electronic energies calculated with the BH and DFT methods in the Gaussian 09 software. These results suggest that the PSO method, due to its low computational cost, could be useful for approximating a molecular structure associated with the global minimum of potential energy, accelerating the prediction of the most stable configuration or conformation, prior to ab initio electronic structure calculation. Full article

With a high proportion of renewable energy sources connected to the distribution network, traditional optimal power flow (OPF) methods face significant challenges including multi-objective co-optimization and dynamic scenario adaptation. This paper proposes a dynamic optimization framework based on the Dynamic Gravitational Search Algorithm (DynaG) for a multi-energy complementary distribution network incorporating wind power, photovoltaic, and energy storage systems. A multi-scenario OPF model is developed considering the time-varying characteristics of wind and solar penetration (low/medium/high), seasonal load variations, and demand response participation. The model aims to minimize both network loss and operational costs, while simultaneously optimizing power supply capability indicators such as power transfer rates and capacity-to-load ratios. Key enhancements to DynaG algorithm include the following: (1) an adaptive gravitational constant adjustment strategy to balance global exploration and local exploitation; (2) an inertial mass updating mechanism constrained to improve convergence for high-dimensional decision variables; and (3) integration of chaotic initialization and dynamic neighborhood search to enhance solution diversity under complex constraints. Validation using the IEEE 33-bus system demonstrates that under 30% penetration scenarios, the proposed DynaG algorithm reduces capacity ratio volatility by 3.37% and network losses by 1.91% compared to non-dominated sorting genetic algorithm III (NSGA-III), multi-objective particle swarm optimization (MOPSO), multi-objective atomic orbital search algorithm (MOAOS), and multi-objective gravitational search algorithm (MOGSA). These results show the algorithm’s robustness against renewable fluctuations and its potential for enhancing the resilience and operational efficiency of high-penetration renewable energy distribution networks. Full article

Extracellular vesicles (EVs), nanoscale membrane-enclosed particles, are natural carriers of proteins and nucleic acids. Microalgae are widely used as a source of bioactive substances in the food and cosmetic industries and definitely have a potential to be used as the producers of EVs for biomedical applications. In this study, the extracellular vesicles isolated from the culture medium of two unicellular microalgae, Chlamydomonas reinhardtii (Chlamy-EVs) and Parachlorella kessleri (Chlore-EVs), were characterized by atomic force microscopy (AFM), cryo-electronic microscopy (cryo-EM), and nanoparticle tracking analysis (NTA). The biocompatibility with human cells in vitro (HEK-293T, DF-2 and A172) and biodistribution in mouse organs and tissues in vivo were tested for both microalgal EVs. An exogenous therapeutic protein, human heat shock protein 70 (HSP70), was successfully loaded to Chlamy- and Chlore-EVs, and its efficient delivery to human glioma and colon carcinoma cell lines has been confirmed. Additionally, in order to search for potential therapeutic biomolecules within the EVs, their proteomes have been characterized. A total of 105 proteins were identified for Chlamy-EVs and 33 for Chlore-EVs. The presence of superoxide dismutase and catalase in the Chlamy-EV constituents allows for considering them as antioxidant agents. The effective delivery of exogenous cargo to human cells and the possibility of the particle yield optimization by varying the microalgae growth conditions make them favorable producers of EVs for biotechnology and biomedical application. Full article

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

Accurate State of Charge (SOC) estimation is critical for optimizing the performance and longevity of lithium-ion batteries (LIBs), which are widely used in applications ranging from electric vehicles to renewable energy storage. Traditional SOC estimation methods, such as Coulomb counting and open-circuit voltage measurement, suffer from cumulative errors and slow response times. This paper proposes a novel machine learning-based approach for SOC estimation by integrating Electrochemical Impedance Spectroscopy (EIS) with the SHapley Additive exPlanations (SHAP) method, Atom Search Optimization (ASO), and Light Gradient Boosting Machine (LightGBM). This study focuses on large-capacity lithium iron phosphate (LFP) batteries (3.2 V, 104 Ah), addressing a gap in existing research. EIS data collected at various SOC levels and temperatures were processed using SHAP for feature extraction (FE), and the ASO–LightGBM model was employed for SOC prediction. Experimental results demonstrate that the proposed SHAP–ASO–LightGBM method significantly improves estimation accuracy, achieving an RMSE of 3.3%, MAE of 1.86%, and R² of 0.99, outperforming traditional methods like LSTM and DNN. The findings highlight the potential of EIS and machine learning (ML) for robust SOC estimation in large-capacity LIBs. Full article

The rising demand for sustainable energy solutions has spurred the development of advanced materials for photovoltaic devices. Among these, transparent conductive oxides (TCOs) play a pivotal role in enhancing device efficiency, particularly in silicon-based solar cells. However, the reliance on indium-based TCOs like ITO raises concerns over cost and material scarcity, prompting the search for more abundant and scalable alternatives. This study focuses on the fabrication and characterization of aluminum-doped zinc oxide (ZnO:Al, AZO) thin films deposited via Atomic Layer Deposition (ALD), targeting their application as transparent conductive oxides in silicon solar cells. The ZnO:Al thin films were synthesized by alternating supercycles of ZnO and Al₂O₃ depositions at 225 °C, allowing precise control of composition and thickness. Structural, optical, and electrical properties were assessed using Scanning Electron Microscopy (SEM), Energy-Dispersive X-ray Spectroscopy (EDS), Transmission Electron Microscopy (TEM), Raman spectroscopy, spectroscopic ellipsometry, and four-point probe measurements. The results confirmed the formation of uniform, crack-free ZnO:Al thin films with a spinel-type ZnAl₂O₄ crystalline structure. Optical analyses revealed high transparency (more than 80%) and tunable refractive indices (1.64 ÷ 1.74); the energy band gap was 2.6 ÷ 3.07 eV, while electrical measurements demonstrated low sheet resistance values, reaching 85 Ω/□ for thicker films. This combination of optical and electrical properties underscores the potential of ALD-grown AZO thin films to meet the stringent demands of next-generation photovoltaics. Integration of Zn:Al thin films into silicon solar cells led to an optimized photovoltaic performance, with the best cell achieving a short-circuit current density of 36.0 mA/cm² and a power conversion efficiency of 15.3%. Overall, this work highlights the technological relevance of ZnO:Al thin films as a sustainable and cost-effective alternative to conventional TCOs, offering pathways toward more accessible and efficient solar energy solutions. Full article

The search for stable, lead-free perovskite materials is critical for developing efficient and environmentally friendly energy solutions. In this study, machine learning methods were applied to predict the bandgap and formation energy of double perovskites, aiming to identify promising photovoltaic candidates. A dataset of 1053 double perovskites was extracted from the Materials Project database, with 50 feature descriptors generated. Feature selection was carried out using Pearson correlation and mRMR methods, and 23 key features for bandgap prediction and 18 key features for formation energy prediction were determined. Four algorithms, including gradient-boosting regression (GBR), random forest regression (RFR), LightGBM, and XGBoost, were evaluated, with XGBoost demonstrating the best performance (R² = 0.934 for bandgap, R² = 0.959 for formation energy; MAE = 0.211 eV and 0.013 eV/atom). The SHAP (Shapley Additive Explanations) analysis revealed that the X-site electron affinity positively influences the bandgap, while the B″-site first and third ionization energies exhibit strong negative effects. Formation energy is primarily governed by the X-site first ionization energy and the electronegativities of the B′ and B″ sites. To identify optimal photovoltaic materials, 4573 charge-neutral double perovskites were generated via elemental substitution, with 2054 structurally stable candidates selected using tolerance and octahedral factors. The XGBoost model predicted bandgaps, yielding 99 lead-free double perovskites with ideal bandgaps (1.3~1.4 eV). Among them, four candidates are known compounds according to the Materials Project database, namely Ca₂NbFeO₆, Ca₂FeTaO₆, La₂CrFeO₆, and Cs₂YAgBr₆, while the remaining 95 candidate perovskites are unknown compounds. Notably, X-site elements (Se, S, O, C) and B″-site elements (Pd, Ir, Fe, Ta, Pt, Cu) favor narrow bandgap formation. These findings provide valuable guidance for designing high-performance, non-toxic photovoltaic materials. Full article