Advanced Hybrid Research Articles

Improving primary frequency response in photovoltaic systems using hybrid inertia and intelligent control techniques

Abstract Low inertia poses a significant challenge to the widespread integration of photovoltaic (PV) systems into the grid, particularly affecting frequency stability. This paper addresses this challenge by proposing an advanced hybrid inertia (AHI) approach, characterized by the integration of real and virtual inertia, combined with the application of intelligent control techniques, to enhance the primary frequency response of a PV system. Internal inertia is provided by a synchronous generator (SG) acting as a compensator, while virtual inertia is generated through a real-time deloading strategy in the PV plant. The AHI is implemented on an isolated grid, utilizing various intelligent control techniques to improve frequency stability. The intelligent techniques employed include genetic algorithms (GA) and fuzzy logic controllers (FLC), which do not require mathematical modeling. This allows them to overcome the nonlinear dynamics of the PV plant and the uncertainties associated with climatic changes. These techniques are applied to the nonlinear components on the generator side, including the governor loop, DC-DC converter loop, and power reserve injection management loop. A frequency fluctuation scenario, induced by generating power perturbations in the proposed system, demonstrates and validates the improvement in frequency stability achieved by the HI and intelligent techniques. All tests are conducted using MATLAB Simulink. Various simulation results show a significant improvement in frequency stability through the incorporation of HI and intelligent control techniques.

First record of metazoan parasites of hybrids between the genera Colossoma and Piaractus in natural environments.

The practice of hybridization is carried out globally in fish farms. Here, we present the first record of the parasitic fauna of hybrids among genus Colossoma and Piaractus in natural environments. We identified a total of 48 hybrids, nine F1 hybrids (nuclear DNA from both species present in the cross) and 38 advanced hybrids (nuclear DNA from one species), both from crosses between Piaractus brachypomus and Piaractus mesopotamicus, and one F1 "tambacu" corresponding to cross between Colossoma macropomum and Piaractus mesopotamicus. This is the first record of Anacanthorus penilabiatus, Anacanthorus toledoensis, Mymarothecium viatorum, Mymarothecium ianwhittington, Haementeria sp., Dadaytrema oxycephala, Rondonia rondoni, and Echinorhynchus gomesi parasitizing hybrids collected in a natural environment. With this, we expand knowledge about the diversity of fish and parasites in the upper Paraná River and warn about the risk that fish escapes can cause in the basin.

Near real-time significant wave height prediction along the coastline of Queensland using advanced hybrid machine learning models

Near real-time significant wave height prediction along the coastline of Queensland using advanced hybrid machine learning models

Advanced feature engineering in microgrid PV forecasting: A fast computing and data-driven hybrid modeling framework

This study introduces an innovative framework designed to forecast the fluctuating short-term generation of photovoltaic (PV) energy in isolated microgrids. The framework relies entirely on solar irradiance data obtained from weather stations located far from the target microgrid. It implements a sophisticated decomposition approach to effectively extract an enriched collection of features from the dataset. Subsequently, a machine learning-based clustering method further enhances the forecasting process by accurately separating the relevant data points. The approach utilizes an advanced two-stage Hybrid Data Linked Model (HDLM) architecture, integrating a Layered Recurrent Neural Framework (LRNF) for prediction and a pattern identification network unit for pattern extraction. This paper demonstrates significant improvements in both the accuracy and effectiveness of estimating PV generation, achieving a mean absolute error of 1.02, a root mean square error of 2.176, and an R-squared score of 0.991. Additionally, the method reduces computing time by 15% after finalizing the input features. A comparative analysis evaluates the superior forecasting capabilities of the HDLM in remote microgrids by benchmarking it against other advanced hybrid deep learning models. The findings highlight the HDLM’s potential to greatly enhance and revolutionize the management and operation of renewable energy systems in remote microgrids.

Exploring tribological and corrosion properties of Al-5052/SiC+CeO2 hybrid surface composites fabricated using friction stir processing

In this study, advanced aluminium metal matrix hybrid surface composites were synthesized using the five-pass friction stir processing (FSP) technique. A blend of Hybrid reinforcement particles, silicon carbide and cerium oxide, were incorporated into the Al-5052 matrix at varying SiC: CeO2 ratios of 100:0, 75:25, 50:50, 25:75, and 0:100. The multi-pass FSP methodology ensured thorough mixing and uniform nanoparticle distribution, resulting in tailored microstructures. The optimal 75:25 SiC: CeO2 ratio exhibited superior microstructural, anti-corrosion, and tribological properties, with the lowest wear rates of 8.3 × 10−9 and 8.8 × 10−9 mm3/m at 15 N and 25 N loads, respectively, and the lowest corrosion rate of 8.06 mm per year compared to other hybrid blends.

Validation of advanced hybrid SPECT/CT system using dynamic anthropomorphic cardiac phantom

ObjectiveMyocardial blood flow (MBF) assessment can provide incremental diagnostic and prognostic information and thus the validation of dynamic SPECT is of high importance. We recently developed a novel cardiac phantom for dynamic SPECT validation and compared its performance against the GE Discovery NM 530c. We now report its use for validation of a new hybrid SPECT/CT System featuring advanced cadmium zinc telluride (CZT) technology in a ring array detector design (StarGuide™, GE HealthCare).MethodsOur recently developed cardiac phantom with injected technetium-99m radiotracer was used to create physiological time activity curves (TACs) for the left ventricular (LV) cavity and the myocardium. The TACs allow the calculation of uptake rate (K1) and MBF. The StarGuide system was used to acquire and process the TACs, and these were compared to the TACs produced by the phantom and its mathematical model. Fifteen (15) experiments with different doses representing various MBF values were conducted, and a standard statistic tool was applied for significance.ResultsThe TACs produced by the StarGuide system had a significant correlation (p < 0.001) with the reference TACs generated by the phantom both for the LV (r = 0.94) and for the myocardium (r = 0.89). The calculated MBF difference between the system and the phantom was 0.14 ± 0.16 ml/min/g and the average relative absolute difference was 13.2 ± 8.1%. A coefficient of variance of ≤ 11% was observed for all MBF subranges. The regional uptake rate values were similar to the global one with a maximum difference of 5%.ConclusionsOur newly developed dynamic cardiac phantom was used for validation of the dynamic hybrid SPECT/CT CZT-based system (StarGuide™, GE). The accuracy and precision of the system for assessing MBF values were high. The new StarGuide system can reliably perform dynamic SPECT acquisitions over a wide range of myocardial perfusion flow rates.

Enhancing mental health prognosis: an investigation of advanced hybrid classifiers with cutting-edge feature engineering and fusion strategies

Enhancing mental health prognosis: an investigation of advanced hybrid classifiers with cutting-edge feature engineering and fusion strategies

An advanced hybrid deep learning model for accurate energy load prediction in smart building

In smart cities, sustainable development depends on energy load prediction since it directs utilities in effectively planning, distributing and generating energy. This work presents a novel hybrid deep learning model including components of the Improved-convolutional neural network (CNN), bidirectional long short-term memory (Bi-LSTM), Graph neural network (GNN), Transformer and Fusion Layer architectures for precise energy load forecasting. Better feature extraction results from the Improved-CNN's dilated convolution and residual block accommodation of wide receptive fields reduced the vanishing gradient problem. By capturing temporal links in both directions, Bi-LSTM networks help to better grasp complicated energy use patterns. Graph neural networks improve predictive capacities across linked systems by characterizing the spatial relationships between energy-consuming units in smart cities. Emphasizing critical trends to guarantee reliable forecasts, transformer models use attention methods to manage long-term dependencies in energy consumption data. Combining CNN, Bi-LSTM, Transformer and GNN component predictions in a Fusion Layer synthesizes numerous data representations to increase accuracy. With Root Mean Square Error of 5.7532 Wh, Mean Absolute Percentage Error of 3.5001%, Mean Absolute Error of 6.7532 Wh and R2 of 0.9701, the hybrid model fared better than other models on the ‘Electric Power Consumption’ Kaggle dataset. This work develops a realistic model that helps informed decision-making and enhances energy efficiency techniques, promoting energy load forecasting in smart cities.

Advanced hybrid malware identification framework for the Internet of Medical Things, driven by deep learning

AbstractThe Internet of Things (IoT) effortlessly enables communication between items on the World Wide Web and other systems. This extensive use of IoTs has created new services and automation in numerous industries, enhancing the standard of living, especially in healthcare. Internet of Medical Things (IoMT) adoption has been beneficial during pandemic conditions by enabling remote patient monitoring and therapy. Nevertheless, the excessive use of IoMT has raised security concerns as it can compromise critical data. This breach in security can result in an inaccurate diagnosis or violate privacy. This research presents a novel approach to hybrid deep learning‐based detection of malware solutions for the IoT. This study uses RNN‐Bi‐LSTM to detect and extract significant features related to an already existing dataset. The proposed model exhibits a detection accuracy of 98.38% when evaluated using these existing datasets. Statistical tests like Mathew co‐relation and Log Loss also indicated reliability of proposed framework. The distinguished feature of our framework is its ability to combine complex deep learning models for IoMT security, which is of economic and scientific importance. It certainly offers a reliable solution for healthcare applications that rely on real‐time functionality and dependency on IoMT systems.

Developing effective optimized machine learning approaches for settlement prediction of shallow foundation

The precise assessment of shallow foundation settlement on cohesionless soils is a challenging geotechnical issue, primarily due to the significant uncertainties related to the factors influencing the settlement. This study aims to create an advanced hybrid machine learning methodology for accurately estimating shallow foundations' settlement (Sm). The initial contribution of the current research is developing and validating a robust hybrid optimization methodology based on an artificial electric field and single candidate optimizer (AEFSCO). This approach is thoroughly tested using various benchmark functions. AEFSCO will also be used to optimize three useful machine learning methods: long short-term memory (LSTM), support vector regression (SVR), and multilayer perceptron neural network (MLPNN) by adjusting their hyperparameters for predicting the settlement of shallow foundations. A database consisting of 189 individual case histories, conducted through various investigations, was used for training and testing the models. The database includes five input parameters and one output. These factors encompassed both the geometric characteristics of the foundation and the properties of the sandy soil. The results demonstrate that employing effective optimization strategies to adjust the ML models’ hyperparameters can significantly improve the accuracy of predicted results. The AEFSCO has increased the coefficient of determination (R2) value of the MLPNN model by 9.3 %, the SVR model by 8 %, and the LSTM model by 22 %. Also, the LSTM-AEFSCO model is more accurate than the SVR-AEFSCO and MLPNN-AEFSCO models. This is shown by the fact that R2 went from 0.9494 to 0.9290 to 0.9903, which is an increase of 4.5 % and 6 %.

Excellence in the management of Advanced Hybrid Closed-Loop Systems: Lessons from the Polish cohort

BackgroundThe aim of the study was to analyze the real-world performance of MiniMed 780G (MM780G) Advanced Hybrid Closed Loop (AHCL) system users from Poland (PL) and compare it to the European region excluding Poland (EU-PL) in order to identify factors contributing to potential differences. The former achieved some of the best Time in Range (TIR) results globally using this technology. MethodsCareLink Personal data uploaded by MM780G system users from August 2020 to December 2022 were analyzed. ResultsThe Polish users (N=1304) on average reached to TIR of 79.1 ± 8.7 % (vs 73.0 ± 10.0 % for EU-PL, N=55659), a TBR<54 mg/dL of 0.6 ± 0.7 % (vs 0.4 ± 0.6 %) and a TBR<70 mg/dL of 2.9 ± 2.1 % (vs 2.1 ± 1.8 %). The adoption rate of optimal settings (i.e, GT=100 mg/dL, AIT=2hr) in PL was high (19.7 % vs 6.3 %), and filtering on optimal setting users led to less pronounced differences in glycemic control between PL and EU-PL. A univariable analysis with post-AHCL TIR showed that geography itself (PL vs EU-PL) is not a significant contributor to a high post-AHCL TIR (p = 0.15), and that much of the Polish post-AHCL TIR can be explained by the high pre-AHCL TIR. ConclusionThe Polish MM780G users achieved better glycemic control than the general European population (excluding Poland). This is largely attributable to the adoption of optimal settings in Poland and the already high glycemic outcomes at system start. As these characteristics can be implemented elsewhere, we believe this outstanding result can be obtained in other countries as well.

Simplified Meal Management in Adults Using an Advanced Hybrid Closed-Loop System.

Background: The advanced hybrid closed-loop (AHCL) algorithm combines automated basal rates and corrections yet requires meal announcement for optimal performance, which poses a challenge for some. We aimed to compare glucose control in adults with type 1 diabetes (T1D) using the MiniMedTM 780G AHCL system, utilizing simplified meal announcement versus precise carbohydrate (CHO) counting. Methods: In a study involving 14 adults with T1D, we evaluated glycemic control during a 13-week "precise phase," followed by two 3- to 4-week simplified meal announcement phases: "fixed one-step" (preset of one personalized fixed CHO amount) and "multistep" (entry of multiples of one, two, or three of these presets depending on meal size estimate). Results: The mean age was 45.7 ± 12.4, and 10 participants were male (71%). Mean baseline HbA1c was 6.8% ± 1.2% and time in range (TIR) was 67.5% ± 16.7%. Comparing the fixed one-step to the precise study phase, TIR was similar (75.4 ± 13% vs. 77.7 ± 9%, P = 0.12), and glucose management indicator (GMI) was slightly higher (6.8 ± 0.4 vs. 6.6 ± 0, P = 0.01). Furthermore, there was less level 1 and 2 hypoglycemia (1.6 ± 1% vs. 2.8 ± 2%, P = 0.03 and 0.3 ± 5% vs. 0.65 ± 1%, P = 0.08) but slightly more level 1 and 2 hyperglycemia (17.1 ± 8% vs. 15.0 ± 7%, P = 0.05 and 5.5 ± 5% vs. 3.6 ± 3%, P = 0.04). When comparing the multistep with the precise phase, GMI was identical (6.6%) and TIR superior (80.5 ± 10% vs. 77.7 ± 9%, P = 0.02). Additionally, there was less level 1 hypoglycemia (1.9 ± 1% vs. 2.8 ± 2%, P = 0.01) and a trend for less level 2 hypoglycemia (0.4 ± 0.7% vs. 0.65 ± 1%, P = 0.08). Conclusions: A simplified meal announcement strategy for adults using the MiniMed 780G system, relying on three increments of a fixed one-step CHO amount, may offer a way to improve glycemic control and ease self-care. For patients with more limitations, using one fixed one-step CHO amount could be a safe alternative to meeting most consensus glycemic targets.

Supermolecule-opitimized defect engineering of rich nitrogen-doped porous carbons for advanced zinc-ion hybrid capacitors.

Pitch-based porous carbons with adjustable surface chemical property and controllable pore structure are regarded as promising cathode materials for aqueous zinc-ion hybrid capacitors (ZIHCs), while its disordered carbon matrix and microstructure as well as insufficient surface defects often result in low Zn2+-storage capacity and poor rate capability of ZIHCs. Herein, a synergetic strategy of self-assembled supermolecule and enriched defective carbon engineering was developed to achieve ultrahigh edge-nitrogen doping for ZIHCs. The crystallite defects and surface structure of porous carbon could be effectively achieved through grafting electronegative oxygen-containing small molecules and high-level nitrogen-containing functional groups between modified polycyclic aromatic hydrocarbon and supermolecule framework. The optimized three-dimensional carbon structure delivered high capacity of 218 mAh g-1 at 0.2 A g-1, fast charge/discharge capability, enhanced energy density (165.4 Wh kg-1) and superior cycling stability (95% retention after 10000 cycles as cathode of ZIHCs). This provided new insight into the controllable synthesis of carbon cathodes for ZIHCs and expects to prepare functional porous carbon by supermolecules and special precursors.

Beyond lithium-ion batteries: Are effective electrodes possible for alkaline and other alkali elements? Exploring ion intercalation in surface-modified few-layer graphene and examining layer quantity and stages

In the pursuit of reliable energy storage solutions, the significance of engineering electrodes cannot be overstated. Previous research has explored the use of surface modifiers (SMs), such as single-side fluorinated graphene, to enhance the thermodynamic stability of ion intercalation when applied atop few-layer graphene (FLG). As we seek alternatives to lithium-ion batteries (LIBs), earth-abundant elements like sodium and potassium have emerged as promising candidates. However, a comprehensive investigation into staging intercalation has been lacking thus far. By delving into staging assemblies, we have uncovered a previously unknown intercalation site that offers the most energetically favorable binding. Here, we study the first three elements in both alkali (Li, Na, K) and alkaline (Be, Mg, Ca) earth metals. Furthermore, the precise mechanism underlying this intercalation system has remained elusive in prior studies. In our work, we employed density functional theory calculations with advanced hybrid functionals to determine the electrical properties at various stages of intercalation. This approach has been proven to yield more accurate and reliable electrical information. Through the analysis of projecting density of states and Mulliken population, we have gained valuable insights into the intricate interactions among the SM, ions, and FLG as the ions progressively insert into the structures. Notably, we expanded our investigation beyond lithium and explored the effectiveness of the SM on ions with varying radii and valence, encompassing six alkali and alkaline earth metals. Additionally, we discovered that the number of graphene layers significantly influences the binding energy. Our findings present groundbreaking concepts for material design, offering diverse and economically viable alternatives to LIBs. Furthermore, they serve as a valuable reference for fine-tuning electrical properties through staging intercalation and the application of SMs.

Synergies of sugar-derived epoxy-silica hybrids and amino-functionalized silica NPs for advanced stone conservation

Innovative approaches to stone conservation materials are essential for addressing the challenges of preserving cultural heritage while meeting environmental and sustainability standards. Based on this premise, this study delves into the synergy between sol-gel processes and nanotechnology to develop advanced epoxy-silica hybrid materials tailored for stone conservation. This investigation specifically targeted the use of amino-functionalized mesoporous silica nanoparticles (NH2-SiO2 NPs) as interactive carriers for natural phenolic biocidal compounds within advanced sugar-based hybrid, demonstrating significant potential in the field of stone conservation. The novel products exhibited improved multifunctional properties attributed to the surface-modified NPs, which facilitated their intimate incorporation into the hybrid network. This integration promoted the creation of homogeneous materials with adapted flexibility, particularly critical for thermal expansion effects, and ensuring mechanical integrity even in outdoor environments. Furthermore, the encapsulation of natural biocidal compounds such as carvacrol and curcumin addressed their intrinsic drawbacks of volatility and coloration effects, preserving their efficacy while minimizing also plasticizing adverse effect on base thermoset. Indeed, the inclusion of curcumin-loaded NH2-SiO2 as dual bactericidal system provided the most favorable compatibility in terms of thermo-mechanical behavior. This system exhibited thermal resistance up to 350 °C and featured inter-joined flexible crystalline domains, distinguished by glass-transition temperatures of 67 and 99 °C. Furthermore, it exhibited enhanced hydrophobic properties reaching contact angles of 105°, and showcased an optimal live/dead ratio response against bacteria. The laboratory scale testing demonstrated a balanced set of features with significant capabilities in both recovering and maintaining the integrity of the lithic substrate, against common degradation patterns induced by prolonged acid exposure.

Microwave-assisted synthesis of perovskite hydroxide-derived Co3O4/SnO2/reduced graphene oxide nanocomposites for advanced hybrid supercapacitor devices

The current article reports a facile, ultrafast, and cost-effective, solid-state microwave (MW) synthetic route for the conversion of perovskite hydroxide (CoSn(OH)6) to crystalline metal oxides (Co3O4 and SnO2) with the help of reduced graphene oxide (rGO) nanosheets. In a domestic MW oven, the Co3O4/SnO2/rGO (CSO-rGO) nanocomposite was synthesized within a quick reaction time of only 30 s. The study deeply focused on analyzing the surface morphology, metal oxide attachment on the surfaces of rGO nanosheets, the specific surface area, and the electrochemical performance of supercapacitor devices from the CSO-rGO nanocomposite. As a positive electrode for supercapacitors, the synthesized hybrid electrode displayed a good capacity (146.4C/g) and enhanced cycling stability (103.2 % after 15,000 cycles). Moreover, the corresponding aqueous hybrid supercapacitor device with MW-synthesized rGO as a negative electrode displayed a maximum energy density of 27 Wh/kg and promising cycling stability of 102.4 % after 10,000 cycles. As a whole, compared to the common time-consuming synthetic approaches, the MW-assisted synthetic approach is highly beneficial in terms of short reaction time, cost-effectiveness, and straightforwardness. The MW synthesis methodology employed in this study can be utilized for analogous composite electrodes that incorporate other layered conductive architectures in addition to metal oxides.

Clutching inertial system for base-isolated liquid storage tanks: Seismic performance and optimal parameters

Liquid storage tanks (LSTs) are susceptible to significant damage during earthquake events, necessitating their continued functionality and additional protection through isolation techniques. The sloshing response and overall base shear of LSTs are critical factors, particularly in base isolated (BI) tanks. This study aims to enhance the seismic resilience of LSTs by leveraging a newly developed advanced inerter-based vibration control methodology for structures. This innovative approach integrates a supplemental clutching inertial system (CIS) with a laminated rubber isolator (LRB). Utilizing an equivalent linearization technique, the study evaluates the equivalent damping and inertance constants to account for the nonlinear behavior of the CIS. These equivalent parameters are then used to assess the stationary peak response of the isolated tank structure, which encompasses sloshing and bearing displacements, forces within the CIS and the isolator, and the total base shear. Further, the analysis employs the stationary power spectral density function (PSDF) model of earthquake excitation by Kanai-Tajimi and the performance of the inerter-based hybrid control strategy is examined by varying system parameters, such as isolation period, isolation damping, CIS inertance mass ratio, and the tank's aspect ratio (i.e., broad or slender). An optimal inertance of the CIS is identified, leading to the least overall base shear for both isolated tank configurations. The impact of these parameters inertance mass ratio of the CIS is also investigated. Subsequently, the isolated tanks are exposed to eleven near-fault (NF) and far-field (FF) real-time earthquake excitations. The study evaluates the CIS's performance as an auxiliary system during these seismic events and contrasts the outcomes with the seismic response under stochastic excitations. The results highlight the effectiveness of the advanced inerter-based hybrid control strategy in reducing the seismic response of isolated tank configurations.

Advanced hybrid membrane constructed with silicon carbide, graphene oxide and functionalized silicon carbide for vanadium permeability, proton conductivity to battery and fuel cell applications

The energy sector is currently exploring eco-friendly energy conversion and storage devices, as an alternative to traditional fossil fuel devices. A unique hybrid proton exchange membrane is developed for proton exchange membrane fuel cells (PEMFC) and vanadium redox flow battery (VRFB) application. Polymeric nanocomposite membranes are effective for the selective and controlled transportation of ions between the electrodes. This study utilizes various modifiers such as GO, SGO, SPES, and SiC, to modify the PES polymer matrix. Analysis of the functional groups confirmed the presence of modifiers and hydroxyl groups on the nanocomposite membrane. Additionally, the use of Field Emission Scanning Electron Microscopy (FESEM) validated the existence of honeycomb and sponge-like voids as well as the surface morphology on the membrane surface. The incorporation of modifiers into the nanocomposite membrane matrix serves as a reliable barrier for the transport of vanadium ions, leading to a significant reduction in vanadium ion permeability across the membrane. The mechanical properties and ion exchange capacity of nanocomposite membranes are enhanced, while the permeability of VO2+ decreases compared to that of the bare PES membrane. The enhancement of proton conductivity is further achieved with the utilization of modifiers in PES polymer. As compared to bare PES membrane, PES/SPES + SGO (5%) exhibits less than half the permeability for vanadium, and PES/SiC shows 44.03 % elongation means twice of bare PES membrane.

Advanced Hybrid Polymer/Ceramic PEO-SnF2 Protective Mechanism for Sodium Metal Anodes

In the face of mounting global energy requirements and pressing environmental issues, the scientific community turned to lithium-metal batteries, celebrated for their superior capacity and efficiency. However, challenges arising from the scarcity and increasing costs of lithium have redirected research efforts towards sodium batteries. Sodium metal anodes, with their remarkable theoretical specific capacity of ~1166 mAh/g, low anode potential of -2.714 V vs standard hydrogen electrode, and cost benefits, are increasingly recognized as promising candidates for conventional energy storage systems. Notwithstanding their advantages, the unstable and fragile solid electrolyte interphase (SEI) due to the spontaneous reaction between metallic Na and a liquid electrolyte remains a significant limitation. As this SEI layer expands, it hinders ion transport, causing increased polarization and diminishing the battery's energy efficiency. Specifically, during the plating process, Na ions are deposited beneath the SEI layer, causing significant expansion. This expansion fractures the fragile SEI, allowing dendrites to grow through these defects. As these dendrites grow, they can pierce the separator, posing a risk of short-circuiting the battery. While numerous studies have proposed designs for protecting sodium metal interphase, to overcome these challenges, this study amalgamates mechano-electrochemical protective strategies to enhance sodium metal anode stability, offering groundbreaking solutions to these challenges.Central to our exploration were tin fluoride (SnF2) and silicon nitride (Si3N4), both established as effective in generating robust artificial SEI layers on the sodium metal surface. These layers, rich in NaF and NaxN respectively, demonstrated a notable improvement in cycling performance, effectively suppressing dendrite growth and enhancing the battery's cycling stability by nearly 3.5 times compared to bare sodium anodes.Building upon these foundational insights, a novel approach was conceptualized: a hybrid protective mechanism combining polyethylene oxide (PEO) with the presence of SnF2 as an additive, is particularly efficacious. This combination was specifically chosen to provide chemical stability, morphological conformality, and mechanical flexibility to accommodate the mechano-electrochemical instability upon sodiation/desodiation processes. Through this novel strategy, we aimed to amalgamate the strengths of both components, ensuring optimal outcomes. This composite artificial SEI under a 0.25 mA/cm2 current density, delivers a cycling performance 10 times superior to bare sodium metal and survived up to 1800 hours of cycling. Impressively, at a high current density of 0.5 mA/cm2, the hybrid system still performed much better than its untreated counterpart and continued cycling for up to 800 hours of cycling. The synergy of PEO and SnF2 remarkably minimized electrolyte decomposition, inhibited dendrite formation, and stabilized Na plating/stripping processes, all of which consolidated its promise for sodium metal battery technology.

PMANet: a time series forecasting model for Chinese stock price prediction

Forecasting stock movements is a crucial research endeavor in finance, aiding traders in making informed decisions for enhanced profitability. Utilizing actual stock prices and correlating factors from the Wind platform presents a potent yet intricate forecasting approach. While previous methodologies have explored this avenue, they encounter challenges including limited comprehension of interrelations among stock data elements, diminished accuracy in extensive series, and struggles with anomaly points. This paper introduces an advanced hybrid model for stock price prediction, termed PMANet. PMANet is founded on Multi-scale Timing Feature Attention, amalgamating Multi-scale Timing Feature Convolution and Ant Particle Swarm Optimization. The model elevates the understanding of dependencies and interrelations within stock data sequences through Probabilistic Positional Attention. Furthermore, the Encoder incorporates Multi-scale Timing Feature Convolution, augmenting the model's capacity to discern multi-scale and significant features while adeptly managing lengthy input sequences. Additionally, the model's proficiency in addressing anomaly points in stock sequences is enhanced by substituting the optimizer with Ant Particle Swarm Optimization. To ascertain the model’s efficacy and applicability, we conducted an empirical study using stocks from four pivotal industries in China. The experimental outcomes demonstrate that PMANet is both feasible and versatile in its predictive capability, yielding forecasts closely aligned with actual values, thereby fulfilling application requirements more effectively.