Foretelling the compressive strength of bamboo using machine learning techniques DOI
Saurabh Dubey, Deepak Gupta,

Mainak Mallik

et al.

Engineering Computations, Journal Year: 2024, Volume and Issue: unknown

Published: Sept. 26, 2024

Purpose The purpose of this research was to develop and evaluate a machine learning (ML) algorithm accurately predict bamboo compressive strength (BCS). Using dataset 150 samples with features such as cross-sectional area, dry weight, density, outer diameter, culm thickness load, various ML algorithms including artificial neural network (ANN), extreme (ELM) support vector regression (SVR) were tested. ELM outperformed others, showing superior accuracy based on metrics like R2, MSE, RMSE, MAE MAPE. study highlights the efficacy in enhancing precision reliability BCS predictions, establishing it valuable tool for assessing strength. Design/methodology/approach This experimentally created using algorithms. Key predictive included load. performance algorithms, ANN, SVR, evaluated. demonstrated coefficient determination (R2), mean square error (MSE), root (RMSE), absolute (MAE) percentage (MAPE), its robustness predicting accurately. Findings found that other ANN BCS. achieved highest key These results indicate is highly effective reliable bamboo, thereby dependability evaluations. Originality/value original application derived data. By comparing establishes ELM’s reliability. findings demonstrate significant potential material prediction, offering novel robust approach evaluating bamboo’s properties. contributes insights into field science engineering, particularly context sustainable construction materials.

Language: Английский

Machine Learning-Based Process Optimization in Biopolymer Manufacturing: A Review DOI Open Access
Ivan Malashin,

D. A. Martysyuk,

В С Тынченко

et al.

Polymers, Journal Year: 2024, Volume and Issue: 16(23), P. 3368 - 3368

Published: Nov. 29, 2024

The integration of machine learning (ML) into material manufacturing has driven advancements in optimizing biopolymer production processes. ML techniques, applied across various stages production, enable the analysis complex data generated throughout identifying patterns and insights not easily observed through traditional methods. As sustainable alternatives to petrochemical-based plastics, biopolymers present unique challenges due their reliance on variable bio-based feedstocks processing conditions. This review systematically summarizes current applications techniques aiming provide a comprehensive reference for future research while highlighting potential enhance efficiency, reduce costs, improve product quality. also shows role algorithms, including supervised, unsupervised, deep

Language: Английский

Citations

5
A Multi-Input Residual Network for Non-Destructive Prediction of Wood Mechanical Properties DOI Open Access

Jingchao Ma,

Zhufang Kuang, Yixuan Fang

et al.

Forests, Journal Year: 2025, Volume and Issue: 16(2), P. 355 - 355

Published: Feb. 16, 2025

Modulus of elasticity (MOE) and modulus rupture (MOR) are crucial indicators for assessing the application value wood. However, traditional physical testing methods mechanical properties wood typically destructive, costly, time-consuming. To efficiently assess these properties, this study proposes a multi-input residual network (MIRN) model, which integrates microscopic images with density data leverages deep learning technology rapid accurate predictions. By using larger convolution kernels to enhance receptive field, model captures fine microstructural features in images. Batch normalization layers were removed from ResNet architecture reduce number parameters improve training stability. Shortcut connections utilized enable deeper architectures address vanishing gradient problem. Two types blocks, convolutional block identity block, defined based on input dimensional changes. The MIRN method, networks, is proposed non-destructive properties. experimental results show that outperforms neural networks (CNNs) ResNet-50 predicting MOE MOR, an R2 0.95 RMSE reduced 46.88, as well 0.85 MOR 0.44. Thus, method offers efficient cost-effective tool processing quality control.

Language: Английский

Citations

0
Atomistic Investigation of Interfacial Interactions in Wood Coated with Layered Double Hydroxide-Induced Stearic Acid DOI
Yuqi Feng, Denvid Lau

˜The œminerals, metals & materials series, Journal Year: 2025, Volume and Issue: unknown, P. 677 - 682

Published: Jan. 1, 2025

Language: Английский

Citations

0
Foretelling the compressive strength of bamboo using machine learning techniques DOI
Saurabh Dubey, Deepak Gupta,

Mainak Mallik

et al.

Engineering Computations, Journal Year: 2024, Volume and Issue: unknown

Published: Sept. 26, 2024

Purpose The purpose of this research was to develop and evaluate a machine learning (ML) algorithm accurately predict bamboo compressive strength (BCS). Using dataset 150 samples with features such as cross-sectional area, dry weight, density, outer diameter, culm thickness load, various ML algorithms including artificial neural network (ANN), extreme (ELM) support vector regression (SVR) were tested. ELM outperformed others, showing superior accuracy based on metrics like R2, MSE, RMSE, MAE MAPE. study highlights the efficacy in enhancing precision reliability BCS predictions, establishing it valuable tool for assessing strength. Design/methodology/approach This experimentally created using algorithms. Key predictive included load. performance algorithms, ANN, SVR, evaluated. demonstrated coefficient determination (R2), mean square error (MSE), root (RMSE), absolute (MAE) percentage (MAPE), its robustness predicting accurately. Findings found that other ANN BCS. achieved highest key These results indicate is highly effective reliable bamboo, thereby dependability evaluations. Originality/value original application derived data. By comparing establishes ELM’s reliability. findings demonstrate significant potential material prediction, offering novel robust approach evaluating bamboo’s properties. contributes insights into field science engineering, particularly context sustainable construction materials.

Language: Английский

Citations

1