Machine Learning-Driven Prediction of Composite Materials Properties Based on Experimental Testing Data

Polymers, Год журнала: 2025, Номер 17(5), С. 694 - 694

Опубликована: Март 5, 2025

The growing demand for high-performance and cost-effective composite materials necessitates advanced computational approaches optimizing their composition properties. This study aimed at the application of machine learning prediction optimization functional properties composites based on a thermoplastic matrix with various fillers (two types fibrous, four dispersed, two nano-dispersed fillers). experimental methods involved material production through powder metallurgy, further microstructural analysis, mechanical tribological testing. analysis revealed distinct structural modifications interfacial interactions influencing key findings indicate that optimal filler selection can significantly enhance wear resistance while maintaining adequate strength. Carbon fibers 20 wt. % improved (by 17–25 times) reducing tensile strength elongation. Basalt 10 provided an effective balance between reinforcement 11–16 times). Kaolin 2 greatly enhanced 45–57 moderate reduction. Coke maximized 9−15 acceptable Graphite ensured wear, as higher concentrations drastically decreased Sodium chloride 5 offered improvement 3–4 minimal impact Titanium dioxide 3 11–12.5 slightly Ultra-dispersed PTFE 1 optimized both work analyzed in detail effect content learning-driven prediction. Regression models demonstrated high R-squared values (0.74 density, 0.67 strength, 0.80 relative elongation, 0.79 intensity), explaining up to 80% variability Despite its efficiency, limitations include potential multicollinearity, lack consideration external factors, need validation under real-world conditions. Thus, approach reduces extensive testing, minimizing waste costs, contributing SDG 9. highlights use polymer design, offering data-driven framework rational choice fillers, thereby sustainable industrial practices.

Язык: Английский

---

Depth determination of simulated biological tissue using X-ray radiography and feature extraction techniques: Evaluation with Bi-LSTM neural network

Journal of Radiation Research and Applied Sciences, Год журнала: 2025, Номер 18(2), С. 101406 - 101406

Опубликована: Март 8, 2025

Язык: Английский

---

The Role of Smart Grid Technologies in Urban and Sustainable Energy Planning

Energies, Год журнала: 2025, Номер 18(7), С. 1618 - 1618

Опубликована: Март 24, 2025

Traditional centralized energy grids struggle to meet urban areas’ increasingly complex demands, necessitating the development of more sustainable and resilient solutions. Smart microgrids offer a decentralized approach that enhances efficiency, facilitates integration renewable sources, improves resilience. This study follows systematic review approach, analyzing literature published in peer-reviewed journals, conference proceedings, industry reports between 2011 2025. The research draws from academic publications institutions alongside regulatory reports, examining actual smart microgrid deployments San Diego, Barcelona, Seoul. Additionally, this article provides real-world case studies New York London, showcasing successful unsuccessful deployments. Brooklyn Microgrid demonstrates peer-to-peer trading, while London faces regulations funding challenges its systems. paper also explores economic policy frameworks such as public–private partnerships (PPPs), localized markets, standardized models enable adoption at scale. While PPPs provide financial infrastructural support for deployment, they introduce stakeholder alignment compliance complexities. Countries like Germany India have successfully used development, leveraging low-interest loans, government incentives, mechanisms encourage innovation technologies. In addition, examines new trends utilization AI quantum computing optimize energy, climate design before outlining future agenda focused on cybersecurity, decarbonization, inclusion technology. Contributions include modular scalable framework, innovative hybrid storage systems, performance-based model suited environment. These contributions help fill gap what is possible today needed systems create foundation cities next century.

Язык: Английский

---

AI-Driven Stacking Ensemble for Predicting Total Power Output of Wave Energy Converters: A Data-Driven Approach to Renewable Energy Processes

Processes, Год журнала: 2025, Номер 13(4), С. 961 - 961

Опубликована: Март 24, 2025

This study develops and evaluates an AI-driven stacked hybrid machine learning model for predicting the total power output of wave energy converters (WECs) across four Australian coastal locations: Adelaide, Perth, Sydney, Tasmania. research enhances prediction accuracy through advanced ensemble techniques while addressing spatial variability in processes. The dataset comprises coordinates readings from 16 fully submerged WECs per location, capturing different regions. Data preprocessing included missing value imputation, duplicate removal, feature transformation via Euclidean distance calculation. Principal component analysis (PCA) was employed to reduce dimensionality preserving critical features influencing generation. To develop accurate model, we a stacking approach using XGBoost, LightGBM, CatBoost as base learners, optimized Optuna hyperparameter tuning with 10-fold cross-validation. A Ridge regression meta-learner combined outputs these models, leveraging their complementary strengths enhance predictive performance. Experimental results demonstrate that consistently outperforms individual enhancing all locations. Sydney exhibited highest (RMSE = 9089.58 W, R2 0.8576), Tasmania posed greatest challenge 45,032.37 0.8378). mitigated overfitting improved generalization by CatBoost. By learning, this provides scalable reliable framework forecasting, facilitating more efficient grid integration resource planning renewable systems.

Язык: Английский

---

A novel dynamic fractional-order discrete grey power model for forecasting China's total solar energy capacity

Engineering Applications of Artificial Intelligence, Год журнала: 2025, Номер 152, С. 110736 - 110736

Опубликована: Апрель 15, 2025

Язык: Английский

---

Data analytics driving net zero tracker for renewable energy

Renewable and Sustainable Energy Reviews, Год журнала: 2024, Номер 208, С. 115061 - 115061

Опубликована: Ноя. 1, 2024

Язык: Английский

---

Analyzing and Forecasting Laboratory Energy Consumption Patterns Using Autoregressive Integrated Moving Average Models

Laboratories, Год журнала: 2024, Номер 2(1), С. 2 - 2

Опубликована: Дек. 30, 2024

This study applied ARIMA modeling to analyze the energy consumption patterns of laboratory equipment over one month, focusing on enhancing management in laboratory. By explicitly examining AC and DC equipment, this obtained detailed daily operating cycles periods inactivity. Advanced differencing diagnostic checks were used verify model accuracy white noise characteristics through enhanced Dickey–Fuller testing residual analysis. The results demonstrate model’s predicting consumption, providing valuable insights into use model. highlights adaptability validity environments, contributing more competent practices.

Язык: Английский

---

Revolutionizing Battery Longevity by Optimising Magnesium Alloy Anodes Performance

Batteries, Год журнала: 2024, Номер 10(11), С. 383 - 383

Опубликована: Окт. 30, 2024

This research explores the enhancement of electrochemical performance in magnesium batteries by optimising alloy anodes, explicitly focusing on Mg-Al and Mg-Ag alloys. The study’s objective was to determine impact composition anode voltage stability overall battery efficiency, particularly under extended cycling conditions. assessed anodes’ behaviour internal resistance across bis(trifluoromethanesulfonyl)imide (Mg(TFSI)2) electrolyte formulations using a systematic setup involving cyclic voltammetry impedance spectroscopy. demonstrated superior performance, with minimal drop lower increase than alloy. results showed that maintained over 85% energy efficiency after 100 cycles, significantly outperforming alloy, which exhibited increased degradation reduction approximately 80%. These findings confirm incorporating aluminium into anodes stabilises enhances mitigating mechanisms. Consequently, is identified as an up-and-coming candidate for use advanced technologies, offering density cycle life improvements. study lays groundwork future refine compositions further boost performance.

Язык: Английский

---

AI-Driven Circular Economy of Enhancing Sustainability and Efficiency in Industrial Operations

Sustainability, Год журнала: 2024, Номер 16(23), С. 10358 - 10358

Опубликована: Ноя. 27, 2024

This study investigates integrating circular economy principles—such as closed-loop systems and economic decoupling—into industrial sectors, including refining, clean energy, electric vehicles. The primary objective is to quantify the impact of practices on resource efficiency environmental sustainability. A mixed-methods approach combines qualitative case studies with quantitative modelling using Brazilian Land-Use Model for Energy Scenarios (BLUES) Autoregressive Integrated Moving Average (ARIMA). These models project long-term trends in emissions reduction optimization. Significant findings include a 20–25% waste production an improvement recycling from 50% 83% over decade. Predictive demonstrated high accuracy, less than 5% deviation actual performance metrics, supported by error metrics such Mean Absolute Percentage Error (MAPE) Root Square (RMSE). Statistical validations confirm reliability these forecasts. highlights potential reduce reliance virgin materials lower carbon while emphasizing critical role policy support technological innovation. integrated offers actionable insights industries seeking sustainable growth, providing robust framework future management applications.

Язык: Английский

---