Strength Model of Cemented Filling Body Based on a Neural Network Algorithm DOI Open Access
Daiqiang Deng, Yihua Liang, Guodong Cao

et al.

Mathematical Problems in Engineering, Journal Year: 2022, Volume and Issue: 2022, P. 1 - 10

Published: April 29, 2022

As one of the key measures for comprehensive management goaf in various mines, filling mining has been recognized by practitioners recent years due to its functions (e.g., resource utilization solid waste and thorough treatment). The performance material is core challenge mining, it influenced settling speed, conveying characteristics, body strength. To understand strength characteristics a cemented composed medium-fine tailings, this study, ratio tests under different content cement, water were conducted. A backpropagation (BP) neural network topology structure was established study. after curing times used as output variable analyze impact on body. 3-Hn-3 structural model employed. When number hidden layers Hn 7, achieved best learning training effect. results show that predicted value, which close measured value (fitting accuracy 92.43–99.92%; average error 0.0792–7.5682%), satisfies engineering requirements. can be employed predict body’s provide good reference change law

Language: Английский

Exploring green mining research trends through web of science: A bibliometric analysis based on VOSviewer and CiteSpace DOI Creative Commons
Yigai Xiao, Hongwei Deng, Peng Wang

et al.

Sustainable Environment, Journal Year: 2025, Volume and Issue: 11(1)

Published: May 20, 2025

Language: Английский

Citations

0
Understanding and Predicting the Usage of Shared Electric Scooter Services on University Campuses DOI Creative Commons
Seyed Mohammad Hossein Moosavi,

Zhenliang Ma,

Danial Jahed Armaghani

et al.

Applied Sciences, Journal Year: 2022, Volume and Issue: 12(18), P. 9392 - 9392

Published: Sept. 19, 2022

Electric vehicles (EVs) have been progressing rapidly in urban transport systems given their potential reducing emissions and energy consumptions. The Shared Free-Floating Scooter (SFFES) is an emerging EV publicized to address the first-/last-mile problem travel. It also offers alternatives for short-distance journeys using cars or ride-hailing services. However, very few SFFES studies carried out developing countries university populations. Currently, many universities are facing increased number of private car travels on campus. study designed explore attitudes perceptions students staff towards usage campus corresponding influencing factors. Three machine learning models were used predict usage. Eleven important factors SFFESs identified via supervised unsupervised feature selection techniques, with top three being daily travel mode, road features (e.g., green spaces) age. random forest model showed highest accuracy predicting frequency (93.5%) selected 11 variables. A simulation-based optimization analysis was further conducted discover characterization users, barriers/benefits safety concerns.

Language: Английский

Citations

14
Shear Strength Estimation of Reinforced Concrete Deep Beams Using a Novel Hybrid Metaheuristic Optimized SVR Models DOI Open Access
Mosbeh R. Kaloop,

Bishwajit Roy,

Kuldeep Chaurasia

et al.

Sustainability, Journal Year: 2022, Volume and Issue: 14(9), P. 5238 - 5238

Published: April 26, 2022

This study looks to propose a hybrid soft computing approach that can be used accurately estimate the shear strength of reinforced concrete (RC) deep beams. Support vector regression (SVR) is integrated with three novel metaheuristic optimization algorithms: African Vultures algorithm (AVOA), particle swarm (PSO), and Harris Hawks (HHO). The proposed models, SVR-AVOA, -PSO, -HHO, are designed compared reference existing models. Multi variables evaluated model evaluate beam’s strength, sensitivity selected in modeling assessed. results indicate SVR-AVOA outperforms other models for prediction. mean absolute error SVR-PSO, SVR-HHO 43.17 kN, 44.09 106.95 respectively. as technique RC beam maximum ±3.39%. Furthermore, analysis shows key parameters (shear span depth ratio, web reinforcement’s yield compressive stirrups spacing, main longitudinal bars reinforcement ratio) efficiently impacted detection beam.

Language: Английский

Citations

12
Predictions of runoff and sediment discharge at the lower Yellow River Delta using basin irrigation data DOI
Shangrui Zhao, Zhen Yang, Shaotong Zhang

et al.

Ecological Informatics, Journal Year: 2023, Volume and Issue: 78, P. 102385 - 102385

Published: Nov. 23, 2023

Language: Английский

Citations

5
Study on Mechanical Properties of Multi-layer Composite Backfill and Constitutive Model Considering Interlayer Inclination DOI
Huazhe Jiao, Qi Zhang, Yunfei Wang

et al.

Mining Metallurgy & Exploration, Journal Year: 2023, Volume and Issue: 40(6), P. 2361 - 2370

Published: Nov. 23, 2023

Language: Английский

Citations

1
Traffic flow prediction based on nonlinear weight decreasing PSO-SVR univariate time series prediction algorithm DOI Creative Commons
Hongyi Li

Applied and Computational Engineering, Journal Year: 2024, Volume and Issue: 75(1), P. 237 - 242

Published: July 5, 2024

The aim of this paper is to investigate the application car flow prediction in field transport order solve problem urban traffic congestion. For purpose, we adopt nonlinear weight decreasing PSO-SVR univariate time series algorithm predict flow, and divide data set into training test according ratio 7:3. By analysing scatterplot line graph between predicted actual values sets, find that effect better, but there a certain deviation. Specifically, scatter plot shows Y=X distribution, have wide range variation relative values. Meanwhile, same trend, value changes more, while less. This may be due long span resulting too many cycles, shortening can reduce number cycles thus improve accuracy. Further analysis MAE for sets both are relatively small, 1.8437 2.6408, respectively, where on large side, overall results model better. Therefore, time-series used provide powerful decision support management departments help them better formulate planning strategies.

Language: Английский

Citations

0
Gold Stock Price Forecasting Based on Nonlinear Weighted Particle Swarm (IPSO) Optimised Support Vector Machine (SVM) Time Series DOI Creative Commons
Han Wang,

Xinqi Dong,

Haichen Qu

et al.

Advances in Economics Management and Political Sciences, Journal Year: 2024, Volume and Issue: 85(1), P. 118 - 124

Published: May 27, 2024

The price of gold, as an important precious metal, is highly volatile and uncertain it affected by the economic political situation in global market. Therefore, forecasting gold great significance for investors, policy makers economists. In this paper, algorithm based on nonlinear weight decreasing PSO-SVR univariate time series prediction proposed price. can help firms to understand market trends fluctuations make more informed decisions. a weighted particle swarm (IPSO) optimised support vector machine (SVM) model, which trained with training set data validated using test data. Y-X scatter plots are plotted predicted real values set, line coordinate system, results show that able predict stock well, be very close each other, both set. model evaluation indexes R2, MAE, MBE MAPE do not deviate much from provide useful information decision enterprises.

Language: Английский

Citations

0
Stamping Process Design of A-Pillar-Upper Inner Plate Based on PSO-SVR Algorithm DOI
J. Wang, Yulong Pan, Zhengrong Li

et al.

Published: Sept. 22, 2023

Aiming at the problem of low efficiency and dependence on experience in stamping process design high strength steel structural parts automobile body, this paper takes A-pillar-upper inner plate as object, designs evaluation index forming quality parametric model process, forms twist springback establishes support vector machine regression with input output. The particle swarm optimization algorithm is used to optimize hyperparameters SVR model, then coupling obtained by learning 80 sample data. Finally, according expected plate, PSO solve reverse, parameters are obtained. After trial production mold parts, measured 0.106, while predicted value 0.101, relative error only 5 %, which proves reliability using method.

Language: Английский

Citations

0
Strength Model of Cemented Filling Body Based on a Neural Network Algorithm DOI Open Access
Daiqiang Deng, Yihua Liang, Guodong Cao

et al.

Mathematical Problems in Engineering, Journal Year: 2022, Volume and Issue: 2022, P. 1 - 10

Published: April 29, 2022

As one of the key measures for comprehensive management goaf in various mines, filling mining has been recognized by practitioners recent years due to its functions (e.g., resource utilization solid waste and thorough treatment). The performance material is core challenge mining, it influenced settling speed, conveying characteristics, body strength. To understand strength characteristics a cemented composed medium-fine tailings, this study, ratio tests under different content cement, water were conducted. A backpropagation (BP) neural network topology structure was established study. after curing times used as output variable analyze impact on body. 3-Hn-3 structural model employed. When number hidden layers Hn 7, achieved best learning training effect. results show that predicted value, which close measured value (fitting accuracy 92.43–99.92%; average error 0.0792–7.5682%), satisfies engineering requirements. can be employed predict body’s provide good reference change law

Language: Английский

Citations

0