Compressive strength prediction models for concrete containing nano materials and exposed to elevated temperatures

Results in Engineering, Journal Year: 2025, Volume and Issue: unknown, P. 103975 - 103975

Published: Jan. 1, 2025

Language: Английский

---

Hybridization of Stochastic Hydrological Models and Machine Learning Methods for Improving Rainfall-Runoff Modelling

Results in Engineering, Journal Year: 2025, Volume and Issue: unknown, P. 104079 - 104079

Published: Jan. 1, 2025

Language: Английский

---

Simulation and multi-objective optimization of argan residues slow pyrolysis for polygeneration of bio-oil, biochar, and gas products

Energy Conversion and Management, Journal Year: 2024, Volume and Issue: 304, P. 118206 - 118206

Published: Feb. 24, 2024

Language: Английский

---

Developing artificial neural networks and response surface methodology for evaluating CO2 absorption into K2CO3/piperazine solution

Case Studies in Chemical and Environmental Engineering, Journal Year: 2024, Volume and Issue: 9, P. 100725 - 100725

Published: April 16, 2024

In this research, artificial neural networks (ANNs) were used to predict the mass transfer flux of CO2 in K2CO3/Piperazine solutions (NCO2). ANN models including multilayer perceptron (MLP) and radial basis function (RBF) modelling. response surface methodology (RSM) was assess impact process variables achieve optimal conditions. The values input parameters, temperature, loading means predicted, coefficient gas liquid transfer, partial pressure CO2, equilibrium obtained 56.94, 0.472, 0.787, 3.321, 0.843, 55786.409 32334.814 respectively. maximom at optimum conditions 449.915 (kmol/m2.s. It has been observed that reducing PCO2* increasing PCO2-b have a greater effect on NCO2 increase. experimental data absorption as case study learn, test, evaluate 0.8, 0.1, 0.1 values, structure MLP includes 4 5 neurons two hidden layers, for RBF it is equal 50. comparison R2 MLP, RBF, RSM shows they 0.9953, 0.9944, 0.9819, This indicates high accuracy compatibility, evidenced by its value. addition, results compared, demonstrated desired accommodation.

Language: Английский

---

Modeling of CO2 solubility in piperazine (PZ) and diethanolamine (DEA) solution via machine learning approach and response surface methodology

Case Studies in Chemical and Environmental Engineering, Journal Year: 2023, Volume and Issue: 8, P. 100457 - 100457

Published: Aug. 14, 2023

With the help of machine-learning algorithms, data-driven models have become increasingly capable predicting CO2 solubility. As part this study, two machine learning approaches are evaluated: artificial neural networks (ANNs) and support vector machines (SVM), as well response surface methodology (RSM) to calculate equilibrium in aqueous solutions containing piperazine (PZ) diethanolamine (DEA). Correlations useful for solubility liquid phase (PZ + DEA) temperature (303, 323, 343.2 K) various partial pressures (100–1000 KPa). The optimization SVM tested multiple kernel functions, such linear, quadratic, cubic, gaussian, alongside different optimizers. cubic function was found proper training SVM. optimum multilayer perceptron (MLP) structure Levenberg-Marquardt algorithm is created with ten neurons one hidden layer. It that MLP network had greatest mean square error (MSE) afterward 7 epochs, equivalent 0.000128, coefficient determination (R2) 0.99947. There a over 0.99 all three models, indicating excellent prediction capabilities.

Language: Английский

---

Valorizing argan residues into biofuels and chemicals through slow pyrolysis

Results in Engineering, Journal Year: 2023, Volume and Issue: 21, P. 101659 - 101659

Published: Dec. 12, 2023

Today's world needs bioresource-derived substitutes for petroleum, chemicals, and fuels. Bio-oil, primarily produced from biomass pyrolysis, is one alternative. However, residues the production process of well-known argan oil have not been thoroughly investigated their potential in pyrolysis. Energy chemical valorization could improve commercial value contribute to regional environmental socio-economic development. In present work, ultimate proximate analyses nut shells (ANS), pulps (AP), press cakes (APC) were first conducted. Then, pyrolysis experiments performed a fixed-bed reactor, bio-oils characterized using GC-MS analysis. The obtained bio-oil yields are 28, 25, 19 wt% ANS, APC, AP, respectively. ANS contains valuable chemicals mainly used pharmaceutical, food, industries. APC-derived can produce pollutants during combustion as it highly nitrogenated compounds. Thus, cannot be directly biofuel, but also exploited production. AP organic highest quantity hydrocarbons has HHV estimated 37 MJ kg−1. Hence, high biofuel bioenergy generation purposes.

Language: Английский

---

Streamlining aromatic content detection in automotive gasoline for environmental protection: Utilizing a rapid and simplified prediction model based on some physical characteristics and regression analysis

Results in Engineering, Journal Year: 2024, Volume and Issue: 21, P. 101771 - 101771

Published: Jan. 13, 2024

As the demand for aromatic content control in gasoline grows order to reduce vehicle particulate emissions, current study established a power regression model of based only on two physical property inputs: relative density (RD) and final boiling point (FBP). The has been developed predict aromatics quantity automotive gasoline, saving time money by avoiding use expensive instruments, inconvenient spectra measurements that require many spectrum input variables. here yields low errors terms average absolute deviation (AAD%), error (Er), standard (SD), root mean squared (RMSE) prediction set, (SEP), with values 4.293%, −0.143%, 0.053, 1.06, 1.58, respectively. When compared earlier spectra-related PLS models, model's applicability evaluation are adequate acceptable.

Language: Английский

---

Machine learning approach with a posteriori-based feature to predict service life of a thermal cracking furnace with coking deposition

Results in Engineering, Journal Year: 2024, Volume and Issue: 22, P. 102349 - 102349

Published: June 1, 2024

A thermal cracking furnace is an important equipment in the petrochemical industry that typically used for breaking long hydrocarbons into short chains and producing coke as a byproduct. Deposition of generated increases temperature at outside coil wall, necessitating regular maintenance to prevent failure. Therefore, this study proposed machine learning approach with posteriori-based feature predict service life runtime The consists two-level model, which aims improve prediction accuracy reduce sensitivity. label classified week range label, can be categorized by classification criteria three classes: weekly, bi-weekly, quarter-weekly. first-level model utilized extract sensor features posterior probability class score. These scores are then processed sorted moving windows generate second-level model. results showed could process variation identify needs, improved 23.94% 17.67% clean coke-contaminated datasets compared conventional respectively. Additionally, most general (quarter-weekly) provided best performance bi-weekly weekly classes. has potential under pseudo-steady state conditions, where coking evolves gradually over time.

Language: Английский

---

Maximizing biodiesel yield of a non-edible chinaberry seed oil via microwave assisted transesterification process using response surface methodology and artificial neural network techniques

Heliyon, Journal Year: 2023, Volume and Issue: 9(11), P. e22031 - e22031

Published: Nov. 1, 2023

In this study, the non-edible Chinaberry Seed Oil (CBO) is converted into biodiesel using microwave assisted transesterification. The objective of effort to maximize yield by optimizing operating parameters, such as catalyst concentration, methanol-oil ratio, reaction speed, and time. designed setup provides a controlled effective approach for turning CBO biodiesel, resulting in encouraging yields reduced times. experimental findings reveal optimal parameters highest (95 %) are concentration 1.5 w/w, ratio 6:1 v/v, speed 400 RPM, period 3 min. interaction several on has been investigated two methodologies: Response Surface Methodology (RSM) Artificial Neural Network (ANN). RSM better modeling parameter interaction, while ANN exhibits lower comparative error when predicting based parameters. percentage improvement prediction found be 12 % compared RSM. This study emphasizes merits both approaches optimization. Furthermore, scaling up microwave-assisted transesterification system industrial production proposes with focus its economic viability environmental effects.

Language: Английский

---

Vulnerability of the rip current phenomenon in marine environments using machine learning models

Results in Engineering, Journal Year: 2023, Volume and Issue: 21, P. 101704 - 101704

Published: Dec. 30, 2023

Hidden and perilous rip currents are one of the primary factors leading to drownings beach swimmers. By identifying coastal areas with highest likelihood generating currents, it becomes possible prevent fatalities mitigate economic losses associated these hazardous currents. Rip characterized as streams water moving towards open sea, forming within area where waves break, due variations in wave-induced radiation stresses pressure along coastline. This study utilized nine different Machine Learning (ML) models, including M5 Model Tree (MT), Multivariate Adaptive Regression Spline (MARS), Gene Expression Programming (GEP), Evolutionary Polynomial (EPR), Random Forest (RF), Support Vector (SVM), Extreme Gradient Boosting (XGBoost), (AdaBoost), Stacked ML estimate Relative Tide Range (RTR) values for 50 southern beaches China. Through this approach, we gathered a reliable dataset from prior research conducted on coast In study, two parameters, namely dimensionless fall velocity parameter (Ω) TR used predict vulnerability current event. The results AI models were assessed by various statistical analyses (Correlation Coefficient [R], Root Mean Square Error [RMSE], violin diagram, heatmap, taylor diagram) training testing stages. Accordingly, MARS model exhibited superior performance compared other accurately predicting RTR value. outcomes substantiated significant effectiveness capability estimating high accuracy. Southern China coasts have relative risk level current, necessitating attention strategic management dangerous managers.

Language: Английский

---