A design of power prediction algorithm based on health assessment optimized neural network DOI Creative Commons
Xin Xie, Feng Huang,

Chengjin He

et al.

Journal of Engineering and Applied Science, Journal Year: 2024, Volume and Issue: 71(1)

Published: April 22, 2024

Abstract Wind power prediction holds significant value for the stability of electrical grid when wind is connected to grid. Using neural networks may have some limitations, such as slow speed and low accuracy. This paper proposes enhance accuracy by optimizing network through health assessment turbines. Firstly, based on turbine actual operating data, a conducted obtain matrix turbine. Then, calculating weights matrix, strategy optimized. Following that, approximation hyperparameters are utilized expedite optimization process. Finally, tests prediction, act optimized back propagation (BP) whale swarm algorithm–support vector regression (WSA-SVR) employed prediction. Results show noticeable optimization: after BP network, increased about 40%, rose 20%; WSA-SVR improved 10%, surged 45%. Further analysis shows that this method can improve most algorithms.

Language: Английский

A PINN-based modelling approach for hydromechanical behaviour of unsaturated expansive soils DOI

K.K. Li,

Zhen‐Yu Yin, Ning Zhang

et al.

Computers and Geotechnics, Journal Year: 2024, Volume and Issue: 169, P. 106174 - 106174

Published: Feb. 27, 2024

Language: Английский

Citations

35
Hybrid LBM and machine learning algorithms for permeability prediction of porous media: A comparative study DOI
Qing Kang,

K.K. Li,

Jinlong Fu

et al.

Computers and Geotechnics, Journal Year: 2024, Volume and Issue: 168, P. 106163 - 106163

Published: Feb. 19, 2024

Language: Английский

Citations

27
Risk assessment of water inrush accident during tunnel construction based on FAHP-I-TOPSIS DOI

He-Qi Kong,

Ning Zhang

Journal of Cleaner Production, Journal Year: 2024, Volume and Issue: 449, P. 141744 - 141744

Published: March 11, 2024

Language: Английский

Citations

20
State-of-the-Art Constitutive Modelling of Frozen Soils DOI Creative Commons

K.K. Li,

Zhen‐Yu Yin, Jilin Qi

et al.

Archives of Computational Methods in Engineering, Journal Year: 2024, Volume and Issue: unknown

Published: April 24, 2024

Abstract In recent decades, the constitutive modelling for frozen soils has attracted remarkable attention from scholars and engineers due to continuously growing constructions in cold regions. Frozen exhibit substantial differences mechanical behaviours compared unfrozen soils, presence of ice complexity phase changes. Accordingly, it is more difficult establish models reasonably capture than soils. This study attempts present a comprehensive review state art which focal topic geotechnical engineering. Various under static dynamic loads are summarised based on their underlying theories. The advantages limitations thoroughly discussed. On this basis, challenges potential future research possibilities soil outlined, including development open databases unified with aid advanced techniques. It hoped that could facilitate describing promote deeper understanding thermo-hydro-mechanical (THM) coupled process occurring

Language: Английский

Citations

14
Towards an improved prediction of soil-freezing characteristic curve based on extreme gradient boosting model DOI Creative Commons

K.K. Li,

Hailong He

Geoscience Frontiers, Journal Year: 2024, Volume and Issue: 15(6), P. 101898 - 101898

Published: July 31, 2024

As an essential property of frozen soils, change unfrozen water content (UWC) with temperature, namely soil-freezing characteristic curve (SFCC), plays significant roles in numerous physical, hydraulic and mechanical processes cold regions, including the heat transfer within soils at land–atmosphere interface, frost heave thaw settlement, as well simulation coupled thermo-hydro-mechanical interactions. Although various models have been proposed to estimate SFCC, their applicability remains limited due derivation from specific soil types, treatments, test devices. Accordingly, this study proposes a novel data-driven model predict SFCC using extreme Gradient Boosting (XGBoost) model. A systematic database for compiled extensive experimental investigations via testing methods was utilized train XGBoost The predicted freezing curves (SFCC, UWC function temperature) well-trained were compared original data three conventional models. results demonstrate superior performance over traditional predicting SFCC. This provides valuable insights future regarding soils.

Language: Английский

Citations

10
Cache Aging with Learning (CAL): A Freshness-Based Data Caching Method for Information-Centric Networking on the Internet of Things (IoT) DOI Creative Commons

Nemat Hazrati,

Sajjad Pirahesh, Bahman Arasteh

et al.

Future Internet, Journal Year: 2025, Volume and Issue: 17(1), P. 11 - 11

Published: Jan. 1, 2025

Information-centric networking (ICN) changes the way data are accessed by focusing on content rather than location of devices. In this model, each piece has a unique name, making it accessible directly name. This approach suits Internet Things (IoT), where generation and real-time processing fundamental. Traditional host-based communication methods less efficient for IoT, ICN better fit. A key advantage is in-network caching, which temporarily stores across various points in network. caching improves access speed, minimizes retrieval time, reduces overall network traffic frequently readily available. However, IoT systems involve constantly updating data, requires managing freshness while also ensuring their validity accuracy. The interactions with cached such as updates, validations, replacements, crucial optimizing system performance. research introduces an ICN-IoT method to manage process IoT. It optimizes sharing only most current valid reducing unnecessary transfers. Routers model calculate freshness, assess its validity, perform cache updates based these metrics. Simulation results four models show that enhances hit ratios, load, delays, outperforming similar methods. proposed uses artificial neural make predictions. These predictions closely match actual values, low error margin 0.0121. precision highlights effectiveness maintaining currentness overhead.

Language: Английский

Citations

1
State of the Art of Coupled Thermo–hydro-Mechanical–Chemical Modelling for Frozen Soils DOI Creative Commons

K.K. Li,

Zhen‐Yu Yin

Archives of Computational Methods in Engineering, Journal Year: 2024, Volume and Issue: unknown

Published: July 29, 2024

Abstract Numerous studies have investigated the coupled multi-field processes in frozen soils, focusing on variation soils and addressing influences of climate change, hydrological processes, ecosystems cold regions. The investigation multi-physics field has emerged as a prominent research area, leading to significant advancements coupling models simulation solvers. However, substantial differences remain among various due insufficient observations in-depth understanding processes. Therefore, this study comprehensively reviews latest process numerical methods, including thermo-hydraulic (TH) coupling, thermo-mechanical (TM) hydro-mechanical (HM) thermo–hydro-mechanical (THM) thermo–hydro-chemical (THC) thermo–hydro-mechanical–chemical (THMC) coupling. Furthermore, primary methods are summarised, continuum mechanics method, discrete or discontinuous simulators specifically designed for heat mass transfer modelling. Finally, outlines critical findings proposes future directions multi-physical modelling soils. This provides theoretical basis mechanism analyses practical engineering applications, contributing advancement management

Language: Английский

Citations

8
GeoLLM: A specialized large language model framework for intelligent geotechnical design DOI
Haitao Xu, Ning Zhang, Zhenyu Yin

et al.

Computers and Geotechnics, Journal Year: 2024, Volume and Issue: 177, P. 106849 - 106849

Published: Oct. 24, 2024

Language: Английский

Citations

7
Effect of Beishan groundwater salinity on the self-sealing performance of compacted GMZ bentonite DOI
Qiong Wang, Xusheng Yan,

Yu Dong

et al.

Environmental Earth Sciences, Journal Year: 2023, Volume and Issue: 82(17)

Published: Aug. 4, 2023

Language: Английский

Citations

16
Soil quality assessment based on machine learning approach for cultivated lands in semi-humid environmental condition part of Black Sea region DOI
Pelin Alaboz, Mehmet Serhat Odabaş, Orhan Dengız

et al.

Archives of Agronomy and Soil Science, Journal Year: 2023, Volume and Issue: 69(15), P. 3514 - 3532

Published: Aug. 17, 2023

ABSTRACTTo manage arable areas according to land resources for future generations, it is crucial determine the quality of soils. The main purpose this study identify soil cultivated lands in semi-humid terrestrial ecosystem Black Sea region. Multi-criteria decision-analysis was performed weighted linear combination approach and standard scoring function (linear-L nonlinear-NL) integrated with GIS techniques interpolation models It tested predict index (SQI) values using artificial neural network (SQIANN). obtained method ranged from 0.444 0.751, while those non-linear 0.315 0.683. As a result, we determined indices cultivation areas. According our statistical analysis, there were no statistically significant differences between SQIL SQIL-ANN same results found SQINL SQINL-ANN. cluster 98.2% similarity SQIL-ANN, 99.2% SQINL-ANN determined. In addition, spatial distribution maps by both clustering analysis geostatistical showed quite lot SQI values.KEYWORDS: ANNmachine learningsoil qualitysustainable agriculturesoil management Disclosure statementNo potential conflict interest reported author(s).Data availability StatementData will be made available on request.Supplementary MaterialSupplemental data article can accessed online at https://doi.org/10.1080/03650340.2023.2248002

Language: Английский

Citations

15