Data-Driven and Machine-Learning-Based Real-Time Viscosity Measurement Using a Compliant Mechanism DOI Creative Commons
Nitin Satpute, Puneet Mahajan,

Abhishek M. Bhagawati

et al.

Applied Sciences, Journal Year: 2024, Volume and Issue: 14(23), P. 10992 - 10992

Published: Nov. 26, 2024

In this work, a novel method of viscosity measurement is proposed using device comprising compliant mechanism, vibration source, and piezoelectric sensor. The source creates linear harmonic vibrations in the mechanism suspended liquid, acceleration response measured located central mass which designed to have necessary directional stiffness. As vibrates, links undergo damping due shearing action fluid because its viscosity. A series measurements are carried out with use water–glycerol solutions such that influenced by fluid’s During working device, immersed liquid whose be measured. recorded as time domain data NI Lab View hardware software, used train machine learning model. Later, regression-based model for estimation dynamic given input. Experiments performed prototype solution within ranging from 10 cP 60 cP. sensor can in-line or handheld instrument quick measurements. achieved high level accuracy, evidenced an R-squared value 0.99, indicating it explains 99% variance data.

Language: Английский

Boosting-Based Machine Learning Applications in Polymer Science: A Review DOI Open Access
Ivan Malashin, В С Тынченко, Andrei Gantimurov

et al.

Polymers, Journal Year: 2025, Volume and Issue: 17(4), P. 499 - 499

Published: Feb. 14, 2025

The increasing complexity of polymer systems in both experimental and computational studies has led to an expanding interest machine learning (ML) methods aid data analysis, material design, predictive modeling. Among the various ML approaches, boosting methods, including AdaBoost, Gradient Boosting, XGBoost, CatBoost LightGBM, have emerged as powerful tools for tackling high-dimensional complex problems science. This paper provides overview applications science, highlighting their contributions areas such structure-property relationships, synthesis, performance prediction, characterization. By examining recent case on techniques this review aims highlight potential advancing characterization, optimization materials.

Language: Английский

Citations

2
Multi-Criteria Optimization of Nanofluid-based Solar Collector for Enhanced Performance: An Explainable Machine Learning-Driven Approach DOI Creative Commons

A. Sankar,

Kritesh Kumar Gupta, Vishal Bhalla

et al.

Energy, Journal Year: 2025, Volume and Issue: unknown, P. 135212 - 135212

Published: Feb. 1, 2025

Language: Английский

Citations

2
Harnessing meta-heuristic, Bayesian, and search-based techniques in optimizing machine learning models for improved energy storage with microencapsulated PCMs DOI
Lotfi Ben Said, Ali Basem, Abbas J. Sultan

et al.

International Communications in Heat and Mass Transfer, Journal Year: 2025, Volume and Issue: 162, P. 108537 - 108537

Published: Jan. 5, 2025

Language: Английский

Citations

1
Accurate prediction of the rheological behavior of MWCNT-Al2O3/water-ethylene glycol nanofluid with metaheuristic-optimized machine learning models DOI
Yi Ru,

Ali B.M. Ali,

Karwan Hussein Qader

et al.

International Journal of Thermal Sciences, Journal Year: 2025, Volume and Issue: 211, P. 109691 - 109691

Published: Jan. 13, 2025

Language: Английский

Citations

1
Integrating artificial neural networks, multi-objective metaheuristic optimization, and multi-criteria decision-making for improving MXene-based ionanofluids applicable in PV/T solar systems DOI Creative Commons
Tao Hai, Ali Basem,

As’ad Alizadeh

et al.

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Nov. 27, 2024

Abstract Optimization of thermophysical properties (TPPs) MXene-based nanofluids is essential to increase the performance hybrid solar photovoltaic and thermal (PV/T) systems. This study proposes a approach optimize TPPs Ionanofluids. The input variables are MXene mass fraction (MF) temperature. optimization objectives include three TPPs: specific heat capacity (SHC), dynamic viscosity (DV), conductivity (TC). In proposed approach, powerful group method data handling (GMDH)-type ANN technique used model in terms variables. obtained models integrated into multi-objective particle swarm (MOPSO) exchange (MOTEO) algorithms, forming three-objective problem. final step, TOPSIS technique, one well-known multi-criteria decision-making (MCDM) approaches, employed identify desirable Pareto points. Modeling results showed that developed for TC, DV, SHC demonstrate strong by R-values 0.9984, 0.9985, 0.9987, respectively. outputs MOPSO revealed points dispersed broad range MFs (0-0.4%). However, temperature these optimal was found be constrained within narrow near maximum value (75 °C). scenarios where TC precedes other objectives, recommended utilizing an MF over 0.2%. Alternatively, when DV holds greater importance, decision-makers can opt ranging from 0.15 0.17%. Also, becomes primary concern, advised base fluid without any additive.

Language: Английский

Citations

5
Synergizing Neural Networks with Multi-Objective Thermal Exchange Optimization and PROMETHEE Decision-Making to Improve PCM-based Photovoltaic Thermal Systems DOI Creative Commons

Li Yongxin,

Ali Basem,

As’ad Alizadeh

et al.

Case Studies in Thermal Engineering, Journal Year: 2025, Volume and Issue: unknown, P. 105851 - 105851

Published: Feb. 1, 2025

Language: Английский

Citations

0
Optimization of nano-finned enclosure-shaped latent heat thermal energy storage units using CFD, RSM, and enhanced hill climbing algorithm DOI Creative Commons
Tao Hai, Ihab Omar, As’ad Alizadeh

et al.

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: April 11, 2025

Language: Английский

Citations

0
Multi-parameter prediction of oil palm fruit quality through near infrared spectroscopy combined with chemometric analysis DOI
Muhammad Achirul Nanda, Kharistya Amaru, S. Rosalinda

et al.

Spectrochimica Acta Part A Molecular and Biomolecular Spectroscopy, Journal Year: 2025, Volume and Issue: 343, P. 126505 - 126505

Published: May 31, 2025

Language: Английский

Citations

0
Integrating artificial Intelligence-Based metaheuristic optimization with Machine learning to enhance Nanomaterial-Containing latent heat thermal energy storage systems DOI Creative Commons
Ali Basem,

Hanaa Kadhim Abdulaali,

As’ad Alizadeh

et al.

Energy Conversion and Management X, Journal Year: 2024, Volume and Issue: unknown, P. 100835 - 100835

Published: Dec. 1, 2024

Language: Английский

Citations

2
Cost-Effective Synthesis of MXene Cadmium Sulfide (CdS) for Heavy Metal Removal DOI Open Access

Justin Linda,

A Geetha,

Vasugi Suresh

et al.

Cureus, Journal Year: 2024, Volume and Issue: unknown

Published: Oct. 5, 2024

Background Environmental contamination resulting from the release of untreated industrial wastewater has emerged as a critical worldwide issue. These effluents frequently have high levels heavy metals and antibiotics, which are bad for aquatic ecosystems human health. Oftentimes, conventional treatment techniques fall short effectively eliminating these pollutants. Innovative materials that may efficiently absorb or break down contaminants contaminated water sources are, therefore, desperately needed. Hydrothermally produced MXene cadmium sulfide (CdS) composites shown great promise an adsorbent material because their special qualities, include surface area, chemical stability, customizable functions improve adsorption capacity antibiotics alike. Aim The aim this study is to produce MXene-CdS nanoparticles in cost-effective method simultaneous removal aqueous pollution control. Methods MXenes were synthesized by selectively etching Ti

Language: Английский

Citations

0