In this article, the process of creating calcium phosphate coatings through plasma electrolytic oxidation was investigated. Calcium phosphate coatings were deposited onto titanium substrates fabricated via the selective laser melting (SLM) method. The correlation between the characteristics of the coating and the applied voltage (200, 250, and 300 V) of PEO was studied. The surface morphology analysis indicates that an increase in applied voltage results in a larger pore size. It was discovered that, when a voltage of 300 V was applied, a layer of hydroxyapatite formed. However, at 300 V, the coating cracked, producing a significantly rough surface. Our analysis of the elemental composition of sample cross sections indicates the presence of TiO₂ layers that are enriched with calcium (Ca) and phosphorus (P). The coefficient of friction and wear rate are primarily influenced by the morphology, pore size, and density of the titanium dioxide layer. Furthermore, a rise in the quantity of the beta phase of the titanium on the surface can be noticed as the applied voltage increases. As a result, it also affects the mechanical and tribological characteristics of the coating. The sample treated to a voltage of 250 V demonstrates a higher resistance to wear and a lower elastic modulus in comparison to the other two coatings.

Plasma electrolytic oxidation (PEO) is often used to improve the physical and mechanical properties of valve metals. This method allows for the formation of thicker and denser metal oxide coatings, which helps to improve physical and mechanical properties, especially the wear and corrosion resistance of the surface. The PEO process is widely used in areas such as mechanical engineering, aerospace, biomedical, and others. This review aims to summarize and explain the fundamental principles of the PEO process, with a focus on the influence of waveform types and their parameters on the properties of PEO coatings. This study found that a sinusoidal waveform promotes the generation of more stable discharges compared to a rectangular waveform, thereby enhancing the corrosion resistance of the coatings. Furthermore, it was demonstrated that using a rectangular waveform with adjustable parameters enables the production of thicker and more wear-resistant coatings. Meanwhile, the application of sawtooth and trapezoidal waveforms reduces sharp current spikes during the onset of discharges, minimizing defect formation and positively influencing the coating formation process. In addition, bipolar and unipolar modes are analyzed, and the promising future directions are discussed.

This study investigates the fabrication, characterization, and computational analysis of a Ti6Al4V porous scaffold for bone tissue engineering (BTE). The main objective is to address the stress-shielding effect caused by the mismatch in the mechanical properties between the scaffold and surrounding bone. An octet-truss architecture was considered to design a highly porous scaffold (with 80.5% porosity) and fabricated using selective laser melting (SLM). The scaffold was then treated with post-processing chemical etching in oxalic acid to remove surface defects and tailor topography. Scanning electron microscopy (SEM) and X-ray diffraction (XRD) revealed that etching effectively removed adhered unmelted powder particles and created a distinct micro-textured strut surface (with increased roughness) that is conducive to osseointegration. The etching process also uniformly thinned down the struts and resulted in 10% mass loss. A compression test gave the scaffold’s compliance-corrected elastic moduli of 4.54 ± 0.18 GPa (pre-etching) and 3.53 ± 0.06 GPa (post-etching). These values closely match with the stiffness of human trabecular bone reported in the literature. The experimental modulus results were validated with a finite element model that predicted 4.188 GPa, which agrees well with the experiment. Furthermore, computational fluid dynamic simulations evaluated a permeability of 8 × 10^–9 m², consistent with transport in bone-like structures.

В работе представлены результаты применения новой структуры свёрточных нейронных сетей (СНС) для обнаружения пожаров на основе аэрофотоснимков. Сформирован обучающий набор данных на основе видеозаписей пожаров, снятых с воздуха в различных условиях. Показано, что предлагаемая свёрточная нейронная сеть достаточно хорошо работает в области обнаружения пожара. Представлены результаты экспериментов на реальных видеопоследовательностях. Предложенный подход обеспечивает высокую точность(precision) 94,78%, полноту(recall) 92,97%, F1-меру 95,42% и хорошие показатели IoU (Intersection over Union), что позволяет сделать вывод об эффективности использования предлагаемой СНС для обнаружения пожаров.

This study focuses on surface modification of aluminum alloys (Al–Si) with high silicon content using plasma electrolytic oxidation (PEO). The influence of Al₂O₃ and SiO₂ particles, introduced both separately and in combination, into a sodium aluminate-based electrolyte during high-frequency treatment (2000 Hz). Examination of surface and cross-sections using a scanning electron microscope SEM showed an increase in the compactness of the coating when Al₂O₃ particles were introduced. The addition of SiO₂ particles tended to promote a smoother surface and a slight reduction in the porosity and defect density. However, when these particles are added together, especially at high concentrations, an increase in structural defects and crack formation is observed. X-ray diffraction analysis revealed that the γ-Al₂O₃ phase was present in all coatings. In the samples with Al₂O₃ addition, the α-Al₂O₃ diffraction signal became stronger compared with the other coatings. Tribological tests revealed that the addition of Al₂O₃ particles significantly improved wear resistance, while the introduction of SiO₂ particles contributed to the stabilization of the friction coefficient. Thus, Al₂O₃ particles were the most effective in enhancing the mechanical properties of the coating.

The increasing deployment of smart meters and Internet of Things technologies has created a demand for intelligent computational systems capable of jointly forecasting electricity consumption, detecting abnormal behavior, and optimizing load management. This study proposes an integrated artificial intelligence-based framework for automated energy metering and consumption management in smart-grid environments. The framework combines a Long Short-Term Memory network for short-term load forecasting, an autoencoder-based model for anomaly detection, and Model Predictive Control for demand-side optimization. The system architecture includes data acquisition, communication, preprocessing, predictive analytics, anomaly monitoring, and decision-support layers. The primary empirical evaluation used 4,380 measured hourly observations (approximately 6 months) from a single administrative building. A separately flagged synthetic temporal extension was retained only as an auxiliary dataset and was excluded from all primary performance metrics. Across five independent model initializations, the final LSTM achieved a MAPE of 3.423 ± 0.555%, an RMSE of 0.336 ± 0.048 kW, and an R ² of 0.973 ± 0.007 on the 633-sequence independent measured test subset. The synthetic extension was maintained as a separately identified auxiliary component and was excluded from all primary training, validation, and independent test metrics. Using a validation-selected reconstruction-error threshold, the autoencoder detected 12 of 30 controlled anomalies in the independent test subset, yielding 100.00% precision, 40.00% recall, and an F1-score of 57.14%. Under the same controlled protocol, One-Class SVM achieved higher recall (53.33%) and F1-score (69.57%), indicating that the autoencoder should be interpreted as an architectural component rather than as the best-performing anomaly detector for the present dataset. A historical proof-of-concept MPC simulation, retained for architectural illustration, reported a 15% reduction in simulated peak demand and a 12% reduction in estimated electricity cost; these values are not interpreted as measured outcomes from the administrative-building experiment. Controlled anomaly injection was used to establish reproducible validation and test labels for the anomaly-detection component. The results demonstrate that the joint integration of forecasting, anomaly detection, and predictive control provides a computationally coherent framework for supporting energy-management efficiency, operational reliability, and data-driven decision-making in intelligent energy systems.