Numerical Simulation and Bayesian Optimization CatBoost Prediction Method for Characteristic Parameters of Veneer Roller Pressing and Defibering DOI Open Access
Qi Wang, Chenglin Yan, Yahui Zhang

et al.

Forests, Journal Year: 2024, Volume and Issue: 15(12), P. 2173 - 2173

Published: Dec. 10, 2024

Defibering equipment is employed in the production of scrimber for purpose wood veneer rolling, cutting, and directional fiber separation. However, current defibering exhibits a notable degree automation deficiency, relying more on manual operation empirical methods process control, which impedes stability quality. This study presented an in-depth finite element analysis roller-pressing equipment, prediction method incorporating numerical simulation ensemble learning was proposed through data collection feature selection. The objective to integrate this into intelligent decision-making system with aim improving productivity effectively stabilizing product results ABAQUS 2020 revealed that roller gap velocity as well geometrical parameters veneer, have significant influence effect. Combining these factors, 702 experiments were devised executed, database constructed based model-building outcomes. strain stress observed served represent force deformation. CatBoost algorithm used establish models key effect, Bayesian Optimization 5-fold cross-validation techniques enabled achieve coefficients determination 0.98 0.97 training test datasets, respectively. Shapley Additive Explanation provide insight contribution each feature, thereby guiding selection simplifying model. show scheme can determine core then practical control strategy online control.

Language: Английский

Building energy consumption prediction using multilayer perceptron neural network-assisted models; comparison of different optimization algorithms DOI
Sadegh Afzal,

Behrooz M. Ziapour,

Afshar Shokri

et al.

Energy, Journal Year: 2023, Volume and Issue: 282, P. 128446 - 128446

Published: July 15, 2023

Language: Английский

Citations

114
Enhanced short-term load forecasting with hybrid machine learning models: CatBoost and XGBoost approaches DOI
Lijie Zhang, Dominik Jánošík

Expert Systems with Applications, Journal Year: 2023, Volume and Issue: 241, P. 122686 - 122686

Published: Nov. 24, 2023

Language: Английский

Citations

46
An advanced framework for net electricity consumption prediction: Incorporating novel machine learning models and optimization algorithms DOI
Xuetao Li, Ziwei Wang, Chengying Yang

et al.

Energy, Journal Year: 2024, Volume and Issue: 296, P. 131259 - 131259

Published: April 9, 2024

Language: Английский

Citations

46
Building energy consumption prediction and optimization using different neural network-assisted models; comparison of different networks and optimization algorithms DOI
Sadegh Afzal, Afshar Shokri,

Behrooz M. Ziapour

et al.

Engineering Applications of Artificial Intelligence, Journal Year: 2023, Volume and Issue: 127, P. 107356 - 107356

Published: Nov. 9, 2023

Language: Английский

Citations

41
Comparative Study of Random Forest and Gradient Boosting Algorithms to Predict Airfoil Self-Noise DOI Creative Commons

Shantaram B. Nadkarni,

G S Vijay,

Raghavendra C. Kamath

et al.

Published: Dec. 12, 2023

Airfoil noise due to pressure fluctuations impacts the efficiency of aircraft and has created significant concern in aerospace industry. Hence, there is a need predict airfoil noise. This paper uses dataset published by NASA (NACA 0012 airfoils) scaled sound using five different input features. Diverse Random Forest Gradient Boost Models are tested with five-fold cross-validation. Their performance assessed based on mean-squared error, coefficient determination, training time, standard deviation. The results show that Extremely Randomized Trees algorithm exhibits most superior highest Coefficient Determination.

Language: Английский

Citations

18
Enhanced multi-layer perceptron for CO2 emission prediction with worst moth disrupted moth fly optimization (WMFO) DOI Creative Commons
Oluwatayomi Rereloluwa Adegboye, Ezgi Deniz Ülker, Afi Kekeli Feda

et al.

Heliyon, Journal Year: 2024, Volume and Issue: 10(11), P. e31850 - e31850

Published: May 27, 2024

This study introduces the Worst Moth Disruption Strategy (WMFO) to enhance Fly Optimization (MFO) algorithm, specifically addressing challenges related population stagnation and low diversity. The WMFO aims prevent local trapping of moths, fostering improved global search capabilities. Demonstrating a remarkable efficiency 66.6 %, outperforms MFO on CEC15 benchmark test functions. Friedman Wilcoxon tests further confirm WMFO's superiority over state-of-the-art algorithms. Introducing hybrid model, WMFO-MLP, combining with Multi-Layer Perceptron (MLP), facilitates effective parameter tuning for carbon emission prediction, achieving an outstanding total accuracy 97.8 %. Comparative analysis indicates that MLP-WMFO model surpasses alternative techniques in precision, reliability, efficiency. Feature importance reveals variables such as Oil Efficiency Economic Growth significantly impact MLP-WMFO's predictive power, contributing up 40 Additionally, Gas Efficiency, Renewable Energy, Financial Risk, Political Risk explain 26.5 13.6 8 6.5 respectively. Finally, WMFO-MLP performance offers advancements optimization modeling practical applications prediction.

Language: Английский

Citations

7
Predicting performance of students by optimizing tree components of random forest using genetic algorithm DOI Creative Commons
Mengyao Chen, Zhengqi Liu

Heliyon, Journal Year: 2024, Volume and Issue: 10(12), P. e32570 - e32570

Published: June 1, 2024

Prediction of student academic performance is still a problem because the limitations existing methods specifically low generalizability and lack interpretability. This study suggests new approach that deals with current problems provides more reliable predictions. The proposed combines information gain (IG) Laplacian score (LS) for feature selection. In this selection scheme, combination IG LS used ranking features then, Sequential Forward Selection mechanism determining most relevant indicators. Also, random forest algorithm genetic introduced multi-class classification. strives to attain accuracy reliability than techniques. case shows strategy can predict students average 93.11 % which minimum improvement 2.25 compared baseline methods. findings were further confirmed by analysis different evaluation metrics (Accuracy, Precision, Recall, F-Measure) prove efficiency mechanism.

Language: Английский

Citations

7
A comprehensive machine learning-based investigation for the index-value prediction of 2G HTS coated conductor tapes DOI Creative Commons
Shahin Alipour Bonab, G.V. Russo, Antonio Morandi

et al.

Machine Learning Science and Technology, Journal Year: 2024, Volume and Issue: 5(2), P. 025040 - 025040

Published: April 30, 2024

Abstract Index-value, or so-called n- value prediction is of paramount importance for understanding the superconductors’ behaviour specially when modeling superconductors needed. This parameter dependent on several physical quantities including temperature, magnetic field’s density and orientation, affects high-temperature superconducting devices made out coated conductors in terms losses quench propagation. In this paper, a comprehensive analysis many machine learning (ML) methods estimating has been carried out. The results demonstrated that cascade forward neural network (CFNN) excels scope. Despite needing considerably higher training time compared to other attempted models, it performs at highest accuracy, with 0.48 root mean squared error (RMSE) 99.72% Pearson coefficient goodness fit ( R -squared). contrast, rigid regression method had worst predictions 4.92 RMSE 37.29% -squared. Also, random forest, boosting methods, simple feed can be considered as middle accuracy model faster than CFNN. findings study not only advance but also pave way applications further research ML plug-and-play codes studies devices.

Language: Английский

Citations

6
Evaluation of students' performance during the academic period using the XG-Boost Classifier-Enhanced AEO hybrid model DOI

Biqian Cheng,

Yuping Liu,

Yunjian Jia

et al.

Expert Systems with Applications, Journal Year: 2023, Volume and Issue: 238, P. 122136 - 122136

Published: Oct. 12, 2023

Language: Английский

Citations

13
Slope stability prediction based on GSOEM-SV: A mobile application practicably deploy in engineering verification DOI
Xiaolong Wang, Shunchuan Wu, Longqiang Han

et al.

Advances in Engineering Software, Journal Year: 2024, Volume and Issue: 192, P. 103648 - 103648

Published: April 11, 2024

Language: Английский

Citations

4